diff --git a/README.md b/README.md index db0fbd88b250cdc2a3cc77521cc1c2cea77c6e87..ceeb6d9e5193763293d3fce76e464340fbce533f 100644 --- a/README.md +++ b/README.md @@ -2,8 +2,8 @@ [![Build Status](https://travis-ci.org/PaddlePaddle/Paddle.svg?branch=develop)](https://travis-ci.org/PaddlePaddle/Paddle) -[![Documentation Status](https://img.shields.io/badge/docs-latest-brightgreen.svg?style=flat)](http://doc.paddlepaddle.org/develop/doc/) -[![Documentation Status](https://img.shields.io/badge/中文文档-最新-brightgreen.svg)](http://doc.paddlepaddle.org/develop/doc_cn/) +[![Documentation Status](https://img.shields.io/badge/docs-latest-brightgreen.svg?style=flat)](http://www.paddlepaddle.org/docs/develop/documentation/en/getstarted/index_en.html) +[![Documentation Status](https://img.shields.io/badge/中文文档-最新-brightgreen.svg)](http://www.paddlepaddle.org/docs/develop/documentation/zh/getstarted/index_cn.html) [![Coverage Status](https://coveralls.io/repos/github/PaddlePaddle/Paddle/badge.svg?branch=develop)](https://coveralls.io/github/PaddlePaddle/Paddle?branch=develop) [![Release](https://img.shields.io/github/release/PaddlePaddle/Paddle.svg)](https://github.com/PaddlePaddle/Paddle/releases) [![License](https://img.shields.io/badge/license-Apache%202-blue.svg)](LICENSE) @@ -36,7 +36,7 @@ Please refer to our [release announcement](https://github.com/PaddlePaddle/Paddl examples: - Optimized math operations through SSE/AVX intrinsics, BLAS libraries - (e.g. MKL, ATLAS, cuBLAS) or customized CPU/GPU kernels. + (e.g. MKL, OpenBLAS, cuBLAS) or customized CPU/GPU kernels. - Highly optimized recurrent networks which can handle **variable-length** sequence without padding. - Optimized local and distributed training for models with high dimensional diff --git a/cmake/cblas.cmake b/cmake/cblas.cmake index 13294c054849092399c60917673c0a6d3dafa85c..6320b17520a687f88993b6f464d9115838b0f96b 100644 --- a/cmake/cblas.cmake +++ b/cmake/cblas.cmake @@ -3,7 +3,7 @@ # It will search MKLML, atlas, OpenBlas, reference-cblas in order. # # If any cblas implementation found, the following variable will be set. -# CBLAS_PROVIDER # one of MKLML, ATLAS, OPENBLAS, REFERENCE +# CBLAS_PROVIDER # one of MKLML, OPENBLAS, REFERENCE # CBLAS_INC_DIR # the include directory for cblas. # CBLAS_LIBS # a list of libraries should be linked by paddle. # # Each library should be full path to object file. @@ -25,42 +25,6 @@ if(WITH_MKLML AND MKLML_INC_DIR AND MKLML_LIB) return() endif() -## Then find atlas. -set(ATLAS_ROOT $ENV{ATLAS_ROOT} CACHE PATH "Folder contains Atlas") -set(ATLAS_INCLUDE_SEARCH_PATHS - ${ATLAS_ROOT}/include - /usr/include - /usr/include/atlas) -set(ATLAS_LIB_SEARCH_PATHS - ${ATLAS_ROOT}/lib - /usr/lib - /usr/lib/blas/atlas - /usr/lib/atlas - /usr/lib/atlas-base # special for ubuntu 14.04. - ) -find_path(ATLAS_INC_DIR NAMES cblas.h - PATHS ${ATLAS_INCLUDE_SEARCH_PATHS}) -find_path(ATLAS_CLAPACK_INC_DIR NAMES clapack.h - PATHS ${ATLAS_INCLUDE_SEARCH_PATHS}) -find_library(ATLAS_CBLAS_LIB NAMES cblas libcblas.so.3 - PATHS ${ATLAS_LIB_SEARCH_PATHS}) -find_library(ATLAS_CLAPACK_LIB NAMES lapack_atlas liblapack_atlas.so.3 - PATHS ${ATLAS_LIB_SEARCH_PATHS}) - -if(ATLAS_CLAPACK_INC_DIR AND ATLAS_INC_DIR AND ATLAS_CBLAS_LIB AND ATLAS_CLAPACK_LIB) - set(CBLAS_FOUND ON) - set(CBLAS_PROVIDER ATLAS) - set(CBLAS_INC_DIR ${ATLAS_INC_DIR} ${ATLAS_CLAPACK_INC_DIR}) - set(CBLAS_LIBRARIES ${ATLAS_CLAPACK_LIB} ${ATLAS_CBLAS_LIB}) - - add_definitions(-DPADDLE_USE_ATLAS) - add_definitions(-DLAPACK_FOUND) - - message(STATUS "Found ATLAS (include: ${ATLAS_INC_DIR}, library: ${CBLAS_LIBRARIES})") - message(STATUS "Found lapack in ATLAS (include: ${ATLAS_CLAPACK_INC_DIR})") - return() -endif() - ## Then find openblas. set(OPENBLAS_ROOT $ENV{OPENBLAS_ROOT} CACHE PATH "Folder contains Openblas") set(OPENBLAS_INCLUDE_SEARCH_PATHS diff --git a/doc/design/fluid-compiler.graffle b/doc/design/fluid-compiler.graffle new file mode 100644 index 0000000000000000000000000000000000000000..c933df2cb855462c52b2d25f7f9a99b95652961d Binary files /dev/null and b/doc/design/fluid-compiler.graffle differ diff --git a/doc/design/fluid-compiler.png b/doc/design/fluid-compiler.png new file mode 100644 index 0000000000000000000000000000000000000000..1b0ffed2039c91a3a00bbb719da08c91c3acf7bb Binary files /dev/null and b/doc/design/fluid-compiler.png differ diff --git a/doc/design/fluid.md b/doc/design/fluid.md new file mode 100644 index 0000000000000000000000000000000000000000..585dc8ef39c0cfb30f470d79f7b27a59ceb5e940 --- /dev/null +++ b/doc/design/fluid.md @@ -0,0 +1,122 @@ +# Design Doc: PaddlePaddle Fluid + +## Why Fluid + +When Baidu developed PaddlePaddle in 2013, the only well-known open source deep learning system at the time was Caffe. However, when PaddlePaddle was open-sourced in 2016, many other choices were available. There was a challenge -- what is the need for open sourcing yet another deep learning framework? + +Fluid is the answer. Fluid is similar to PyTorch and TensorFlow Eager Execution, which describes the "process" of training or inference using the concept of a model. In fact in PyTorch, TensorFlow Eager Execution and Fluid, there is no concept of a model at all. The details are covered in the sections below. Fluid is currently more extreme in the above mentioned idea than PyTorch and Eager Execution, and we are trying to push Fluid towards the directions of a compiler and a new programming language for deep learning. + +## The Evolution of Deep Learning Systems + +Deep learning infrastructure is one of the fastest evolving technologies. Within four years, there have already been three generations of technologies invented. + +| Existed since | model as sequence of layers | model as graph of operators | No model | +|--|--|--|--| +| 2013 | Caffe, Theano, Torch, PaddlePaddle | | | +| 2015 | | TensorFlow, MxNet, Caffe2, ONNX, n-graph | | +| 2016 | | | PyTorch, TensorFlow Eager Execution, PaddlePaddle Fluid | + +From the above table, we see that the deep learning technology is evolving towards getting rid of the concept of a model. To understand the reasons behind this direction, a comparison of the *programming paradigms* or the ways to program deep learning applications using these systems, would be helpful. The following section goes over these. + +## Deep Learning Programming Paradigms + +With the systems listed as the first or second generation, e.g., Caffe or TensorFlow, an AI application training program looks like the following: + +```python +x = layer.data("image") +l = layer.data("label") +f = layer.fc(x, W) +s = layer.softmax(f) +c = layer.mse(l, s) + +for i in xrange(1000): # train for 1000 iterations + m = read_minibatch() + forward({input=x, data=m}, minimize=c) + backward(...) + +print W # print the trained model parameters. +``` + +The above program includes two parts: + +1. The first part describes the model, and +2. The second part describes the training process (or inference process) for the model. + +This paradigm has a well-known problem that limits the productivity of programmers. If the programmer made a mistake in configuring the model, the error messages wouldn't show up until the second part is executed and `forward` and `backward` propagations are performed. This makes it difficult for the programmer to debug and locate a mistake that is located blocks away from the actual error prompt. + +This problem of being hard to debug and re-iterate fast on a program is the primary reason that programmers, in general, prefer PyTorch over the older systems. Using PyTorch, we would write the above program as following: + +```python +W = tensor(...) + +for i in xrange(1000): # train for 1000 iterations + m = read_minibatch() + x = m["image"] + l = m["label"] + f = layer.fc(x, W) + s = layer.softmax(f) + c = layer.mse(l, s) + backward() + +print W # print the trained model parameters. +``` + +We can see that the main difference is the moving the model configuration part (the first step) into the training loop. This change would allow the mistakes in model configuration to be reported where they actually appear in the programming block. This change also represents the model better, or its forward pass, by keeping the configuration process in the training loop. + +## Describe Arbitrary Models for the Future + +Describing the process instead of the model also brings Fluid, the flexibility to define different non-standard models that haven't been invented yet. + +As we write out the program for the process, we can write an RNN as a loop, instead of an RNN as a layer or as an operator. A PyTorch example would look like the following: + +```python +for i in xrange(1000): + m = read_minibatch() + x = m["sentence"] + for t in xrange x.len(): + h[t] = the_step(x[t]) +``` + +With Fluid, the training loop and the RNN in the above program are not really Python loops, but just a "loop structure" provided by Fluid and implemented in C++ as the following: + +```python +train_loop = layers.While(cond) +with train_loop.block(): + m = read_minibatch() + x = m["sentence"] + rnn = layers.While(...) + with rnn.block(): + h[t] = the_step(input[t]) +``` + +An actual Fluid example is described [here](https://github.com/PaddlePaddle/Paddle/blob/a91efdde6910ce92a78e3aa7157412c4c88d9ee8/python/paddle/v2/fluid/tests/test_while_op.py#L36-L44). + +From the example, the Fluid programs look very similar to their PyTorch equivalent programs, except that Fluid's loop structure, wrapped with Python's `with` statement, could run much faster than just a Python loop. + +We have more examples of the [`if-then-else`](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/if_else_op.md) structure of Fluid. + +## Turing Completeness + +In computability theory, a system of data-manipulation rules, such as a programming language, is said to be Turing complete if it can be used to simulate any Turing machine. For a programming language, if it provides if-then-else and loop, it is Turing complete. From the above examples, Fluid seems to be Turing complete; however, it is noteworthy to notice that there is a slight difference between the `if-then-else` of Fluid and that of a programming language. The difference being that the former runs both of its branches and splits the input mini-batch into two -- one for the True condition and another for the False condition. This hasn't been researched in depth if this is equivalent to the `if-then-else` in programming languages that makes them Turing-complete. Based on a conversation with [Yuang Yu](https://research.google.com/pubs/104812.html), it seems to be the case but this needs to be looked into in-depth. + +## The Execution of a Fluid Program + +There are two ways to execute a Fluid program. When a program is executed, it creates a protobuf message [`ProgramDesc`](https://github.com/PaddlePaddle/Paddle/blob/a91efdde6910ce92a78e3aa7157412c4c88d9ee8/paddle/framework/framework.proto#L145) that describes the process and is conceptually like an [abstract syntax tree](https://en.wikipedia.org/wiki/Abstract_syntax_tree). + +There is a C++ class [`Executor`](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/executor.h), which runs a `ProgramDesc`, similar to how an interpreter runs a Python program. + +Fluid is moving towards the direction of a compiler, which is explain in more detail later in this article. + +## Backward Compatibility of Fluid + +Given all the advantages from the removal of the concept of a *model*, hardware manufacturers might still prefer the existence of the concept of a model, so it would be easier for them to support multiple frameworks all at once and could run a trained model during inference. For example, Nervana, a startup company acquired by Intel, has been working on an XPU that reads the models in the format known as [n-graph](https://github.com/NervanaSystems/ngraph). Similarly, [Movidius](https://www.movidius.com/) is producing a mobile deep learning chip that reads and runs graphs of operators. The well-known [ONNX](https://github.com/onnx/onnx) is also a file format of graphs of operators. + +For Fluid, we can write a converter that extracts the parts in the `ProgramDesc` protobuf message, converts them into a graph of operators, and exports the graph into the ONNX or n-graph format. + +## Towards a Deep Learning Language and the Compiler + +We can change the `if-then-else` and loop structure a little bit in the above Fluid example programs, to make it into a new programming language, different than Python. + +Even if we do not invent a new language, as long as we get the `ProgramDesc` message filled in, we can write a transpiler, which translates each invocation to an operator, into a C++ call to a kernel function of that operator. For example, a transpiler that weaves the CUDA kernels outputs an NVIDIA-friendly C++ program, which can be built using `nvcc`. Another transpiler could generate MKL-friendly code that should be built using `icc` from Intel. More interestingly, we can translate a Fluid program into its distributed version of two `ProgramDesc` messages, one for running on the trainer process, and the other one for the parameter server. For more details of the last example, the [concurrent programming design](concurrent_programming.md) document would be a good pointer. The following figure explains the proposed two-stage process: + +![](fluid-compiler.png) diff --git a/doc/design/images/multigpu_allreduce.graffle b/doc/design/images/multigpu_allreduce.graffle new file mode 100644 index 0000000000000000000000000000000000000000..cb5bc420ceafe8ba4c87694d44ee4e5e4ad06779 Binary files /dev/null and b/doc/design/images/multigpu_allreduce.graffle differ diff --git a/doc/design/images/multigpu_allreduce.png b/doc/design/images/multigpu_allreduce.png new file mode 100644 index 0000000000000000000000000000000000000000..87a1b3e8f6dd4a713ec9df9f0037d1da04e9178a Binary files /dev/null and b/doc/design/images/multigpu_allreduce.png differ diff --git a/doc/design/images/multigpu_before_convert.graffle b/doc/design/images/multigpu_before_convert.graffle new file mode 100644 index 0000000000000000000000000000000000000000..6c35ab1b21fb76ceae82d3693ed0d085b5bc0855 Binary files /dev/null and b/doc/design/images/multigpu_before_convert.graffle differ diff --git a/doc/design/images/multigpu_before_convert.png b/doc/design/images/multigpu_before_convert.png new file mode 100644 index 0000000000000000000000000000000000000000..9c8f7711165d80a2fa3911280fdee91855a401b1 Binary files /dev/null and b/doc/design/images/multigpu_before_convert.png differ diff --git a/doc/design/paddle_nccl.md b/doc/design/paddle_nccl.md new file mode 100644 index 0000000000000000000000000000000000000000..c7dac70998a6cfec3a6d2fc72b698ff9722e6805 --- /dev/null +++ b/doc/design/paddle_nccl.md @@ -0,0 +1,65 @@ +# Design Doc: NCCL support in Paddle Fluid + +## Abstract + +This Design Doc refers to the NCCL feature in paddle. We propose an approach to support NCCL library both on a single machine and multiple machines. We wrapper the NCCL primitives `Broadcast`, `Allreduce`, `Reduce` as operators to utilize Multi-GPU powers in one script. + + +## Motivation + +[NCCL](https://developer.nvidia.com/nccl) is a NVIDIA library support Multi-GPU communicating and optimized for NVIDIA GPUs, it provides routines such as all-gather, all-reduce, broadcast, reduce, reduce-scatter, that can achieve high bandwidth over PCIe and NVLink high-speed interconnect. With NCCL library, we can easily accelerate the training in parallel. + +- Pros +1. easily plug-in with [NCCL2](https://developer.nvidia.com/nccl) library. +1. high performance in NVIDIA GPUs. +1. MPI like primitives, which have low learning cost for users. + +- Cons +1. Only design for NVIDIA GPUs, not a general multi-device solution. +1. Although NCCL1 is opensourced under BSD license, but NCCL2 is not opensourced anymore. + +At the beginning of training, the framework needs to distribute the same parameters to every GPU, and merge the gradients at any time user interests. + +As a result, during training, we need the operations of peer to peer copy between different GPUs, aggregating gradients/parameters from GPUs, and broadcasting parameters to GPUs. Every GPU only need to run the operator with correct place information. + +Besides, it needs interfaces to synchronize model update with each different GPU Cards. + +## Implementation + +As mentioned above, we wrap the NCCL routines as several kinds of operators. Need to note that NCCL need to create Communicator between gpu at the beginning, so there is a NCCLInit operator created. + +### Transpiler + +To be compatible with [parameter server design doc](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/ops/dist_train.md), the transpiler compiles the user defined operation graph into sub-graphs to be executed on different devices. + +1. The user-defined model will be a single device program + +2. Broadcast/Reduce operators between GPUs will be inserted into the program, even for the multi-node, may insert the `Send`, `Recv` operator. + + *Broadcast, AllReduce in a single machine. And Broadcast, AllReduce, [Send, Recv](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/ops/dist_train.md#graph-converter) in multiple machines* + + + +After compiling, the graph as shows + + + +Operators are added to the sub-graphs. Every GPU assigned a role of `rank0`, `rank1` etc. + +- **Broadcast**. Broadcast operator distribute initialized parameter to all the GPUs from the GPU who owns it. e.g. from`rank0` GPU. +- **AllReduce**. AllReduce operator synchronizes parameters/gradients between GPUs. AllReduce implemented in the Ring-Based communicating method, avoid of the bottle neck in a single GPU. + +Need to notice that AllReduce operator force GPUs synchronized at that point. The whole training process in asynchronous or synchronous mode depends on the AllReduce point in the graph. + +As it shown in the picture, when each GPU compute the gradient of `W`, followed with a `AllReduce` operator, accumulate the `dW` to full batch of data, then run the optimize process individually and apply the gradient to its `W`. + +- **AllReduce** + Need to note that our AllReduce operator is a ring-base AllReduce implementation. If we use the NCCL2 AllReduce primitive, every GPU optimized full batch of data, wasted (n-1) GPU compute resources. In addition, NCCL2 built-in AllReduce will only utilize the communicating resource during synchronization, then update the gradient will be a subsequent phase. In fact, we can amortize the update gradient time cost into the communicating phase. The process is +1. Every parameter has its root card. That card will responsible for aggregating the gradients from GPUs. +2. The whole model's parameter will be hashed to different root card, ensure the load balance between GPUs. +3. Logically neighberhood card will start send parameter to the next one. After one round, the parameter main card will aggregate the full gradients. +4. Then the root card will optimize the parameter. +5. This parameter card will send its optimized result to its neighberhood, then the neighberhood will send parameter to its next one. +6. Finish the sychronization round. + +The total time cost will be 2 * (n-1) * per-parameter-send-time, we reach the goal of amortize the upgrade time into communicating phase. diff --git a/doc/design/support_new_device.md b/doc/design/support_new_device.md new file mode 100644 index 0000000000000000000000000000000000000000..fd23dc211a35fdc9d87bc9233fcf4e90254da748 --- /dev/null +++ b/doc/design/support_new_device.md @@ -0,0 +1,248 @@ +# Design Doc: Supporting new Device/Library + +## Background + +Deep learning has a high demand for computing resources. New high-performance devices and computing libraries are appearing very frequently. Deep learning frameworks have to integrate these high-performance devices and computing libraries flexibly and efficiently. + +On one hand, hardware and computing libraries usually do not have a one-to-one correspondence. For example,Intel CPUs support Eigen and MKL computing libraries while Nvidia GPUs support Eigen and cuDNN computing libraries. We have to implement operator specific kernels for each computing library. + +On the other hand, users usually do not want to care about the low-level hardware and computing libraries when writing a neural network configuration. In Fluid, `Layer` is exposed in `Python`, and `Operator` is exposed in `C++`. Both `Layer` and `Operator` are hardware independent. + +So, how to support a new Device/Library in Fluid becomes a challenge. + + +## Basic: Integrate A New Device/Library + +For a general overview of fluid, please refer to the [overview doc](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/howto/read_source.md). + +There are mainly three parts that we have to consider while integrating a new device/library: + +- Place and DeviceContext: indicates the device id and manages hardware resources + +- Memory and Tensor: malloc/free data on certain device + +- Math Functor and OpKernel: implement computing unit on certain devices/libraries + +### Place and DeviceContext + + +#### Place +Fluid uses class [Place](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/platform/place.h#L55) to represent different devices and computing libraries. There are inheritance relationships between different kinds of `Place`. + +``` + | CPUPlace --> MKLDNNPlace +Place --| CUDAPlace --> CUDNNPlace + | FPGAPlace +``` + +And `Place` is defined as follows: + +``` +typedef boost::variant Place; +``` + +#### DeviceContext + +Fluid uses class [DeviceContext](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/platform/device_context.h#L30) to manage the resources in different hardwares, such as CUDA stream in `CDUADeviceContext`. There are also inheritance relationships between different kinds of `DeviceContext`. + + +``` + /-> CPUDeviceContext --> MKLDeviceContext +DeviceContext ----> CUDADeviceContext --> CUDNNDeviceContext + \-> FPGADeviceContext +``` + +An example of Nvidia GPU is as follows: + +- DeviceContext + + +``` +class DeviceContext { + virtual Place GetPlace() const = 0; +}; +``` + + +- CUDADeviceContext + + +``` +class CUDADeviceContext : public DeviceContext { + Place GetPlace() const override { return place_; } +private: + CUDAPlace place_; + cudaStream_t stream_; + cublasHandle_t cublas_handle_; + std::unique_ptr eigen_device_; // binds with stream_ +}; +``` + +- CUDNNDeviceContext + +``` +class CUDNNDeviceContext : public CUDADeviceContext { + private: + cudnnHandle_t cudnn_handle_; +}; +``` + + +### Memory and Tensor + + +#### memory module + +Fluid provides the following [memory interfaces](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/memory/memory.h#L36): + +``` +template +void* Alloc(Place place, size_t size); + +template +void Free(Place place, void* ptr); + +template +size_t Used(Place place); +``` + +To implementing these interfaces, we have to implement MemoryAllocator for different Devices + + +#### Tensor + +[Tensor](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/tensor.h#L36) holds data with some shape in a specific Place. + +```cpp +class Tensor { + public: + /*! Return a pointer to mutable memory block. */ + template + inline T* data(); + + /** + * @brief Return a pointer to mutable memory block. + * @note If not exist, then allocation. + */ + template + inline T* mutable_data(platform::Place place); + + /** + * @brief Return a pointer to mutable memory block. + * + * @param[in] dims The dimensions of the memory block. + * @param[in] place The place of the memory block. + * + * @note If not exist, then allocation. + */ + template + inline T* mutable_data(DDim dims, platform::Place place); + + /*! Resize the dimensions of the memory block. */ + inline Tensor& Resize(const DDim& dims); + + /*! Return the dimensions of the memory block. */ + inline const DDim& dims() const; + + private: + /*! holds the memory block if allocated. */ + std::shared_ptr holder_; + + /*! points to dimensions of memory block. */ + DDim dim_; +}; +``` + +`Placeholder` is used to delay memory allocation; that is, we can first define a tensor, using `Resize` to configure its shape, and then call `mutuable_data` to allocate the actual memory. + +```cpp +paddle::framework::Tensor t; +paddle::platform::CPUPlace place; +// set size first +t.Resize({2, 3}); +// allocate memory on CPU later +t.mutable_data(place); +``` + + + +### Math Functor and OpKernel + +Fluid implements computing units based on different DeviceContexts. Some computing units are shared between operators. This common part will be put in operators/math directory as basic Functors. + +Let's take [MaxOutFunctor](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/operators/math/maxouting.h#L27) as an example: + +The interface is defined in header file. + +``` +template +class MaxOutFunctor { + public: + void operator()(const DeviceContext& context, const framework::Tensor& input, + framework::Tensor* output, int groups); +}; +``` + +CPU implemention is in .cc file + +``` +template +class MaxOutFunctor { + public: + void operator()(const platform::CPUDeviceContext& context, + const framework::Tensor& input, framework::Tensor* output, + int groups) { + ... + } +}; +``` + +CUDA implemention is in .cu file + +``` +template +class MaxOutFunctor { + public: + void operator()(const platform::CUDADeviceContext& context, + const framework::Tensor& input, framework::Tensor* output, + int groups) { + ... + } +}; +``` + + +We get computing handle from a concrete DeviceContext, and make compution on tensors. + +The implemention of `OpKernel` is similar to math functors, the extra thing we need to do is to register the OpKernel in a global map. + +Fluid provides different register interfaces in op_registry.h + + +Let's take [Crop](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/operators/crop_op.cc#L134) operator as an example: + +In .cc file: + +``` +REGISTER_OP_CPU_KERNEL(crop, ops::CropKernel); +REGISTER_OP_CPU_KERNEL( + crop_grad, ops::CropGradKernel); +``` + +In .cu file: + +``` +REGISTER_OP_CUDA_KERNEL(crop, ops::CropKernel); +REGISTER_OP_CUDA_KERNEL( + crop_grad, ops::CropGradKernel); +``` + + +## Advanced topics: How to switch between different Device/Library + +Generally, we will impelement OpKernel for all Device/Library of an Operator. We can easily train a Convolutional Neural Network in GPU. However, some OpKernel is not sutibale on a specific Device. For example, crf operator can only run on CPU, whereas most other operators can run at GPU. To achieve high performance in such circumstance, we have to switch between different Device/Library. + + +We will discuss how to implement an efficient OpKernel switch policy. + +- TBD diff --git a/doc/faq/build_and_install/index_cn.rst b/doc/faq/build_and_install/index_cn.rst index f1677e216f31d79b53ac29a0afbf6fbb886a0dcd..a2bdeead7841393fdfe90c78e5b91d9e61678a24 100644 --- a/doc/faq/build_and_install/index_cn.rst +++ b/doc/faq/build_and_install/index_cn.rst @@ -14,7 +14,7 @@ $ export CUDA_SO="$(\ls usr/lib64/libcuda* | xargs -I{} echo '-v {}:{}') $(\ls /usr/lib64/libnvidia* | xargs -I{} echo '-v {}:{}')" $ export DEVICES=$(\ls /dev/nvidia* | xargs -I{} echo '--device {}:{}') - $ docker run ${CUDA_SO} ${DEVICES} -it paddledev/paddlepaddle:latest-gpu + $ docker run ${CUDA_SO} ${DEVICES} -it paddlepaddle/paddle:latest-gpu 更多关于Docker的安装与使用, 请参考 `PaddlePaddle Docker 文档 `_ 。 diff --git a/doc/getstarted/build_and_install/docker_install_cn.rst b/doc/getstarted/build_and_install/docker_install_cn.rst index f78b1fb0e11aa028a4b7abb5270740b97f8039e9..1eb06e4182d40c3be20d71e37b34009905eaf9d6 100644 --- a/doc/getstarted/build_and_install/docker_install_cn.rst +++ b/doc/getstarted/build_and_install/docker_install_cn.rst @@ -114,7 +114,7 @@ PaddlePaddle Book是为用户和开发者制作的一个交互式的Jupyter Note .. code-block:: bash - nvidia-docker run -it -v $PWD:/work paddledev/paddle:latest-gpu /bin/bash + nvidia-docker run -it -v $PWD:/work paddlepaddle/paddle:latest-gpu /bin/bash **注: 如果没有安装nvidia-docker，可以尝试以下的方法，将CUDA库和Linux设备挂载到Docker容器内：** @@ -122,7 +122,7 @@ PaddlePaddle Book是为用户和开发者制作的一个交互式的Jupyter Note export CUDA_SO="$(\ls /usr/lib64/libcuda* | xargs -I{} echo '-v {}:{}') $(\ls /usr/lib64/libnvidia* | xargs -I{} echo '-v {}:{}')" export DEVICES=$(\ls /dev/nvidia* | xargs -I{} echo '--device {}:{}') - docker run ${CUDA_SO} ${DEVICES} -it paddledev/paddle:latest-gpu + docker run ${CUDA_SO} ${DEVICES} -it paddlepaddle/paddle:latest-gpu **关于AVX：** diff --git a/doc/getstarted/build_and_install/docker_install_en.rst b/doc/getstarted/build_and_install/docker_install_en.rst index d7acc7aeb744b19d83acb520d07c8551168dd096..5a46c598f2248c7912169a9e77b16851230c1d2e 100644 --- a/doc/getstarted/build_and_install/docker_install_en.rst +++ b/doc/getstarted/build_and_install/docker_install_en.rst @@ -122,7 +122,7 @@ GPU driver installed before move on. .. code-block:: bash - nvidia-docker run -it -v $PWD:/work paddledev/paddle:latest-gpu /bin/bash + nvidia-docker run -it -v $PWD:/work paddlepaddle/paddle:latest-gpu /bin/bash **NOTE: If you don't have nvidia-docker installed, try the following method to mount CUDA libs and devices into the container.** @@ -130,7 +130,7 @@ GPU driver installed before move on. export CUDA_SO="$(\ls /usr/lib64/libcuda* | xargs -I{} echo '-v {}:{}') $(\ls /usr/lib64/libnvidia* | xargs -I{} echo '-v {}:{}')" export DEVICES=$(\ls /dev/nvidia* | xargs -I{} echo '--device {}:{}') - docker run ${CUDA_SO} ${DEVICES} -it paddledev/paddle:latest-gpu + docker run ${CUDA_SO} ${DEVICES} -it paddlepaddle/paddle:latest-gpu **About AVX:** diff --git a/doc/getstarted/concepts/src/infer.py b/doc/getstarted/concepts/src/infer.py new file mode 100644 index 0000000000000000000000000000000000000000..4cc58dfee0bd6dade0340b4fd0ee1adb49ffebf6 --- /dev/null +++ b/doc/getstarted/concepts/src/infer.py @@ -0,0 +1,18 @@ +import paddle.v2 as paddle +import numpy as np + +paddle.init(use_gpu=False) +x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(2)) +y_predict = paddle.layer.fc(input=x, size=1, act=paddle.activation.Linear()) + +# loading the model which generated by training +with open('params_pass_90.tar', 'r') as f: + parameters = paddle.parameters.Parameters.from_tar(f) + +# Input multiple sets of data，Output the infer result in a array. +i = [[[1, 2]], [[3, 4]], [[5, 6]]] +print paddle.infer(output_layer=y_predict, parameters=parameters, input=i) +# Will print: +# [[ -3.24491572] +# [ -6.94668722] +# [-10.64845848]] diff --git a/doc/getstarted/concepts/src/train.py b/doc/getstarted/concepts/src/train.py index 8aceb23406a476f08639cc6223cdf730b728a705..4bccbfca3c70c12aec564e2cae3b8ca174b68777 100644 --- a/doc/getstarted/concepts/src/train.py +++ b/doc/getstarted/concepts/src/train.py @@ -26,6 +26,11 @@ def event_handler(event): if event.batch_id % 1 == 0: print "Pass %d, Batch %d, Cost %f" % (event.pass_id, event.batch_id, event.cost) + # product model every 10 pass + if isinstance(event, paddle.event.EndPass): + if event.pass_id % 10 == 0: + with open('params_pass_%d.tar' % event.pass_id, 'w') as f: + trainer.save_parameter_to_tar(f) # define training dataset reader diff --git a/doc/getstarted/concepts/use_concepts_cn.rst b/doc/getstarted/concepts/use_concepts_cn.rst index c243083794bb3c4659242de99b3b2715af9d7c24..e695ff283e2e806377a51c559b37e8068360a4ff 100644 --- a/doc/getstarted/concepts/use_concepts_cn.rst +++ b/doc/getstarted/concepts/use_concepts_cn.rst @@ -147,4 +147,9 @@ PaddlePaddle支持不同类型的输入数据，主要包括四种类型，和 .. literalinclude:: src/train.py :linenos: +使用以上训练好的模型进行预测，取其中一个模型params_pass_90.tar，输入需要预测的向量组，然后打印输出： + +.. literalinclude:: src/infer.py + :linenos: + 有关线性回归的实际应用，可以参考PaddlePaddle book的 `第一章节 `_。 diff --git a/doc/howto/dev/contribute_to_paddle_cn.md b/doc/howto/dev/contribute_to_paddle_cn.md index 699390145226ec2b65fdf5122db187e1d30d669e..3e0bf7b3973079a2063d33b6be4fe8a9dc5c07bb 100644 --- a/doc/howto/dev/contribute_to_paddle_cn.md +++ b/doc/howto/dev/contribute_to_paddle_cn.md @@ -76,18 +76,18 @@ no changes added to commit (use "git add" and/or "git commit -a") ## 构建和测试 -编译 PaddlePaddle 的源码以及生成文档需要多种开发工具。为了方便大家，我们的标准开发流程是把这些工具都装进一个Docker image，称为*开发镜像*，通常名字是 `paddle:dev`。然后所有用 `cmake && make` 的地方（比如IDE配置里）都用 `docker run paddle:dev`来代替。 +编译 PaddlePaddle 的源码以及生成文档需要多种开发工具。为了方便大家，我们的标准开发流程是把这些工具都装进一个Docker image，称为*开发镜像*，通常名字是 `paddle:latest-dev` 或者 `paddle:[version tag]-dev` 如 `paddle:0.11.0-dev`。然后所有用 `cmake && make` 的地方（比如IDE配置里）都用 `docker run paddle:latest-dev`来代替。 如要build这个开发镜像，在源码目录树的根目录中运行： ```bash -➜ docker build -t paddle:dev . +➜ docker build -t paddle:latest-dev . ``` 随后可以用这个开发镜像开始build PaddlePaddle的源码。比如如果要build一个不依赖GPU，但是支持AVX指令集，并且包括unit tests的PaddlePaddle，可以： ```bash -➜ docker run -v $(pwd):/paddle -e "WITH_GPU=OFF" -e "WITH_AVX=ON" -e "WITH_TEST=ON" paddle:dev +➜ docker run -v $(pwd):/paddle -e "WITH_GPU=OFF" -e "WITH_AVX=ON" -e "WITH_TESTING=ON" paddle:latest-dev ``` 这个过程除了编译PaddlePaddle为 `./build/libpaddle.so`，并且输出一个 `./build/paddle.deb`文件之外，还会输出一个 `build/Dockerfile`。我们只需要运行下面命令把编译好的PaddlePaddle打包成一个*生产镜像*（`paddle:prod`）： @@ -99,7 +99,7 @@ no changes added to commit (use "git add" and/or "git commit -a") 如果要运行所有的单元测试，可以用如下命令： ```bash -➜ docker run -it -v $(pwd):/paddle paddle:dev bash -c "cd /paddle/build && ctest" +➜ docker run -it -v $(pwd):/paddle paddle:latest-dev bash -c "cd /paddle/build && ctest" ``` 关于构建和测试的更多信息，请参见[这篇文档](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/getstarted/build_and_install/docker_install_cn.rst)。 diff --git a/doc/howto/dev/new_op_cn.md b/doc/howto/dev/new_op_cn.md index 44dbeecbbdf39f5d8f529c63b9a52d71da26aede..757a5840bca4c8028e362789ec95bb03d261d2c1 100644 --- a/doc/howto/dev/new_op_cn.md +++ b/doc/howto/dev/new_op_cn.md @@ -1,17 +1,18 @@ # 如何写新的Operator - [概念简介](#概念简介) - - [实现C++类](#实现C++类) - - [定义ProtoMaker类](#定义ProtoMaker类) - - [定义Operator类](#定义Operator类) - - [定义OpKernel类](#定义OpKernel类) - - [注册Operator](#注册Operator) + - [实现C++类](#实现c类) + - [定义ProtoMaker类](#定义protomaker类) + - [定义Operator类](#定义operator类) + - [定义OpKernel类](#定义opkernel类) + - [注册Operator](#注册operator) - [编译](#编译) - - [绑定Python](#绑定Python) + - [绑定Python](#绑定python) - [实现单元测试](#实现单元测试) - - [前向Operator单测](#前向Operator单测) - - [反向Operator单测](#反向Operator单测) + - [前向Operator单测](#前向operator单测) + - [反向Operator单测](#反向operator单测) - [编译和执行](#编译和执行) + - [注意事项](#注意事项) ## 概念简介 @@ -43,7 +44,7 @@ Kernel实现 | CPU、CUDA共享Kernel实现在`.h`文件中，否则，CPU ## 实现C++类 -### 1. 定义ProtoMaker类 +### 定义ProtoMaker类 矩阵乘法的公式：$Out = X * Y$, 可见该计算由两个输入，一个输出组成。 @@ -100,7 +101,7 @@ The equation is: Out = scale*X - `AddAttr("scale", "...").SetDefault(1.0);` : 增加`scale`系数，作为参数属性，并且设置默认值为1.0。 -### 2. 定义Operator类 +### 定义Operator类 下面的点实现了MulOp的定义： @@ -149,7 +150,7 @@ MulOp(const std::string &type, const framework::VariableNameMap &inputs, 通常`OpProtoMaker`和`Op`类的定义写在`.cc`文件中，和下面将要介绍的注册函数一起放在`.cc`中 -### 3. 定义OpKernel类 +### 定义OpKernel类 `MulKernel`继承自`framework::OpKernel`，带有下面两个模板参数: @@ -177,6 +178,7 @@ MulOp(const std::string &type, const framework::VariableNameMap &inputs, math::matmul(*X, false, *Y, false, 1, Z, 0, device_context); } }; + ``` 需要注意：**不同设备(CPU、CUDA)共享一个Op定义，是否则共享同一个`OpKernel`，取决于`Compute`调用的函数是否支持不同设备。** @@ -188,7 +190,7 @@ MulOp(const std::string &type, const framework::VariableNameMap &inputs, 到此，前向Op实现完成。接下来，需要在`.cc`文件中注册该op和kernel。 反向Op类的定义，反向OpKernel的定义与前向Op类似，这里不再赘述。**但需注意反向Op没有`ProtoMaker`**。 -### 4. 注册Operator +### 注册Operator - 在`.cc`文件中注册前向、反向Op类，注册CPU Kernel。 @@ -220,7 +222,7 @@ MulOp(const std::string &type, const framework::VariableNameMap &inputs, ops::MulGradKernel); ``` -### 5. 编译 +### 编译 运行下面命令可以进行编译： @@ -236,6 +238,7 @@ make mul_op 单测包括对比前向Op不同设备(CPU、CUDA)的实现、对比反向OP不同设备(CPU、CUDA)的实现、反向Op的梯度测试。下面介绍介绍[`MulOp`的单元测试](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/framework/tests/test_mul_op.py)。 +### 前向Operator单测 Op单元测试继承自`OpTest`。各项更加具体的单元测试在`TestMulOp`里完成。测试Operator，需要： @@ -273,8 +276,7 @@ Op单元测试继承自`OpTest`。各项更加具体的单元测试在`TestMulOp def test_check_grad_ingore_y(self): self.check_grad( ['X'], 'Out', max_relative_error=0.5, no_grad_set=set('Y')) - - ``` + ``` 上面的代码首先导入依赖的包，下面是对`setUp`函数中操作的重要变量的详细解释： @@ -282,6 +284,8 @@ Op单元测试继承自`OpTest`。各项更加具体的单元测试在`TestMulOp - `self.inputs` : 定义输入，类型为`numpy.array`，并初始化。 - `self.outputs` : 定义输出，并在Python脚本中完成与operator同样的计算逻辑，返回Python端的计算结果。 +### 反向operator单测 + 而反向测试中： - `test_check_grad_normal`中调用`check_grad`使用数值法检测梯度正确性和稳定性。 - 第一个参数`["X", "Y"]` : 指定对输入变量`X`、`Y`做梯度检测。 @@ -290,7 +294,7 @@ Op单元测试继承自`OpTest`。各项更加具体的单元测试在`TestMulOp - `test_check_grad_ingore_x`和`test_check_grad_ingore_y`分支用来测试只需要计算一个输入梯度的情况。 -### 编译和执行单元测试 +### 编译和执行 `python/paddle/v2/framework/tests` 目录下新增的 `test_*.py` 单元测试会被自动加入工程进行编译。 diff --git a/doc/howto/dev/new_op_en.md b/doc/howto/dev/new_op_en.md index 510233306c23ba0e8c83b8b057778ea6b875bf6a..fe86936bc12cc2fb88d653429e250f71a478dfb6 100644 --- a/doc/howto/dev/new_op_en.md +++ b/doc/howto/dev/new_op_en.md @@ -1,8 +1,8 @@ # How to write a new operator - [Background](#background) - - [Implementing C++ Types](#implementing-c++-types) - - [Defining ProtoMaker](#defining-protoMaker) + - [Implementing C++ Types](#implementing-c-types) + - [Defining ProtoMaker](#defining-protomaker) - [Defining Operator](#defining-operator) - [Registering Operator](#registering-operator) - [Compilation](#compilation) @@ -41,7 +41,7 @@ Let's take matrix multiplication operator, [MulOp](https://github.com/PaddlePadd ## Implementing C++ Types -### 1. Defining Class ProtoMaker +### Defining ProtoMaker Matrix Multiplication can be written as $Out = X * Y$, meaning that the operation consists of two inputs and pne output. @@ -98,7 +98,7 @@ There are two changes in this example: - `AddAttr("scale", "...").SetDefault(1.0);` adds `scale`constant as an attribute, and sets the default value to 1.0. -### 2. Defining Operator +### Defining Operator The following code defines the interface for MulOp: @@ -147,7 +147,7 @@ MulOp(const std::string &type, const framework::VariableNameMap &inputs, Usually `OpProtoMaker` and `Op`'s type definitions are written in `.cc` files, which also include the registration methods introduced later. -### 3. Defining OpKernel +### Defining OpKernel `MulKernel` inherits `framework::OpKernel`, which includes the following templates: @@ -188,7 +188,7 @@ This concludes the forward implementation of an operator. Next its operation and The definition of its corresponding backward operator, if applicable, is similar to that of an forward operator. **Note that a backward operator does not include a `ProtoMaker`**. -### 4. Registering Operator +### Registering Operator - In `.cc` files, register forward and backward operator classes and the CPU kernel. @@ -220,7 +220,7 @@ The definition of its corresponding backward operator, if applicable, is similar ops::MulGradKernel); ``` -### 5. Compilation +### Compilation Run the following commands to compile. @@ -284,8 +284,7 @@ A forward operator unit test inherits `unittest.TestCase` and defines metaclass def test_check_grad_ingore_y(self): self.check_grad( ['X'], 'Out', max_relative_error=0.5, no_grad_set=set('Y')) - - ``` + ``` Get its output, and compare it with the forward operator's own output. The code above first loads required packages. In addition, we have @@ -294,6 +293,8 @@ The code above first loads required packages. In addition, we have - `self.inputs` defines input, with type `numpy.array` and initializes it. - `self.outputs` defines output and completes the same operator computation in the Python script, and returns its result from the Python script. +### Testing Backward Operators + Some key points in checking gradient above include: - `test_normal` calls `check_grad` to validate scaling tests' correctness and stability through numeric methods. diff --git a/doc/howto/read_source.md b/doc/howto/read_source.md new file mode 100644 index 0000000000000000000000000000000000000000..383acb0c8251043c3c6bbf309d2e07bf0074cd4f --- /dev/null +++ b/doc/howto/read_source.md @@ -0,0 +1,67 @@ +# PaddlePaddle Fluid Source Code Overview + +Examples: https://github.com/PaddlePaddle/Paddle/tree/develop/python/paddle/v2/fluid/tests/book + +Core: https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/framework + +Operator: https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/operators + +Optimizer: https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/optimizer + +Memory: https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/memory + +# Compile Time + +The following **defines** the NN. The definition goes into this [protocol buffer](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/framework.proto). + +```python +x = fluid.layers.data(name='x', shape=[13], dtype='float32') +y = fluid.layers.data(name='y', shape=[1], dtype='float32') + +y_predict = fluid.layers.fc(input=x, size=1, act=None) +cost = fluid.layers.square_error_cost(input=y_predict, label=y) +avg_cost = fluid.layers.mean(x=cost) + +sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001) +sgd_optimizer.minimize(avg_cost) +``` + +- Variables: `x`, `y`, `y_predict`, `cost` and `avg_cost`. [Python](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/fluid/framework.py#L93) +- Layers: `fluid.layers.data`, `fluid.layers.fc` and `fluid.layers.mean` are layers. [Python](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/fluid/layers.py) + - Every Layer has one or more operators and variables/parameters + - All the operators are defined at [`paddle/operators/`](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/operators). Other worth-looking files: + - Base class: [`paddle/framework/operator.h`](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/operator.h) + - Operator Registration: [`paddle/framework/op_registry.h`](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/op_registry.h) + - Operator Lookup: [`paddle/framework/op_info.h`](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/op_info.h) +- Optimizer: `fluid.optimizer.SGD`. It does the following + - Add backward operators. [[Python](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/fluid/backward.py), [C++](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/backward.cc)] + - Add optimizer operators. [[Python](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/fluid/optimizer.py), [C++](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/optimizer)] + +# Run Time + +The following **evaluates** the NN. Instantiates all the variables, operators. + +```python +place = fluid.CPUPlace() +feeder = fluid.DataFeeder(place=place, feed_list=[x, y]) +exe = fluid.Executor(place) + +# Allocate memory. Initialize Parameter. +exe.run(fluid.default_startup_program()) + +# Allocate memory. Do computation. +exe.run(fluid.default_main_program(), + feed=feeder.feed(data), + fetch_list=[avg_cost]) +``` + +- Place: `place`. one of CPU, GPU or FPGA. [C++](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/platform/place.h) + - The device handle are at [paddle/platform/device_context.h](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/platform/device_context.h) +- Executor: `fluid.Executor(place)`. [[Python](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/fluid/executor.py), [C++](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/executor.cc)] + - Feeds the data: `feed=feeder.feed(data)` + - Evaluates all the operators + - Fetches the result: `fetch_list=[avg_cost]` +- Other worth looking files: + - Scope: [paddle/framework/scope.h](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/scope.h). Where all the variables live + - Variable: [paddle/framework/variable.h](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/variable.h). Where all the data (most likely tensors) live + - Tensor: [paddle/framework/tensor.h](https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/tensor.h). Where we allocate memory through [`paddle/memory/`](https://github.com/PaddlePaddle/Paddle/tree/develop/paddle/memory) diff --git a/doc/mobile/cross_compiling_for_ios_cn.md b/doc/mobile/cross_compiling_for_ios_cn.md index 9da48e7f2119ce901fbb3abab73400df27be16d2..d5196d9a4c93c7692d2a624ec7d0650e32806338 100644 --- a/doc/mobile/cross_compiling_for_ios_cn.md +++ b/doc/mobile/cross_compiling_for_ios_cn.md @@ -18,11 +18,11 @@ PaddlePaddle为交叉编译提供了工具链配置文档[cmake/cross_compiling/ - `CMAKE_SYSTEM_NAME`，CMake编译的目标平台，必须设置为`iOS`。在设置`CMAKE_SYSTEM_NAME=iOS`后，PaddlePaddle的CMake系统会自动编译所有的第三方依赖库，并且强制设置一些PaddlePaddle参数的值（`WITH_C_API=ON`、`WITH_GPU=OFF`、`WITH_AVX=OFF`、`WITH_PYTHON=OFF`、`WITH_RDMA=OFF`）。 - `WITH_C_API`，是否编译C-API预测库，必须设置为ON。在iOS平台上只支持使用C-API来预测。 -- `WITH_SWIG_PY`，必须设置为ON。在iOS平台上不支持通过swig调用来训练或者预测。 +- `WITH_SWIG_PY`，必须设置为`OFF`。在iOS平台上不支持通过swig调用来训练或者预测。 iOS平台可选配置参数： -- `IOS_PLATFORM`，可设置为`OS/SIMULATOR`，默认值为`OS`。 +- `IOS_PLATFORM`，可设置为`OS`（默认值）或`SIMULATOR`。 - `OS`，构建目标为`arm`架构的iPhone或者iPad等物理设备。 - `SIMULATOR`，构建目标为`x86`架构的模拟器平台。 - `IOS_ARCH`，目标架构。针对不同的`IOS_PLATFORM`，可设置的目标架构如下表所示，默认编译所有架构： diff --git a/doc/mobile/cross_compiling_for_ios_en.md b/doc/mobile/cross_compiling_for_ios_en.md new file mode 100644 index 0000000000000000000000000000000000000000..aa390cd61f3fbd75e5a3b342f3559e76da35a918 --- /dev/null +++ b/doc/mobile/cross_compiling_for_ios_en.md @@ -0,0 +1,120 @@ +# PaddlePaddle Compiling Guide for iOS + +This tutorial will walk you through cross compiling the PaddlePaddle library for iOS from the source in MacOS. + +## Preparation + +Apple provides Xcode for cross-compiling and IDE for iOS development. Download from App store or [here](https://developer.apple.com/cn/xcode/). To verify your installation, run command as follows + +```bash +$ xcodebuild -version +Xcode 9.0 +Build version 9A235 +``` + +## Cross-compiling configurations + +PaddlePaddle provides cross-compiling toolchain configuration documentation [cmake/cross_compiling/ios.cmake](https://github.com/PaddlePaddle/Paddle/blob/develop/cmake/cross_compiling/ios.cmake), which has some default settings for frequently used compilers. + +There are some mandatory environment variables need to be set before cross compiling PaddlePaddle for iOS: + +- `CMAKE_SYSTEM_NAME`, CMake compiling target platform name, has to be `iOS`. PaddlePaddle CMake will compile all the third party dependencies and enforce some parameters (`WITH_C_API=ON`, `WITH_GPU=OFF`, `WITH_AVX=OFF`, `WITH_PYTHON=OFF`,`WITH_RDMA=OFF`) when this variable is set with value `iOS`. + +- `WITH_C_API`, Whether to compile inference C-API library, has to be `ON`, since C-API is the only supported interface for inferencing in iOS. +- `WITH_SWIG_PY`, has to be `OFF`. It's not supported to inference or train via swig in iOS. + +Optional environment variables for iOS are: + +- `IOS_PLATFORM`, either `OS` (default) or `SIMULATOR`. + - `OS`, build targets ARM-based physical devices like iPhone or iPad. + - `SIMULATOR`, build targets x86 architecture simulators. +- `IOS_ARCH`, target architecture. By default, all architecture types will be compiled. If you need to specify the architecture to compile for, please find valid values for different `IOS_PLATFORM` settings from the table below: + + + + + + + + + + + + + + + + + + + + + + +
IOS_PLATFORMIOS_ARCH
OSarmv7, armv7s, arm64
SIMULATORi386, x86_64
+ +- `IOS_DEPLOYMENT_TARGET`, minimum iOS version to deployment, `7.0` by default. +- `IOS_ENABLE_BITCODE`, whether to enable [Bitcode](https://developer.apple.com/library/content/documentation/IDEs/Conceptual/AppDistributionGuide/AppThinning/AppThinning.html#//apple_ref/doc/uid/TP40012582-CH35-SW3), values can be `ON/OFF`, `ON` by default. +- `IOS_USE_VECLIB_FOR_BLAS`, whether to use [vecLib](https://developer.apple.com/documentation/accelerate/veclib) framework for BLAS computing. values can be `ON/OFF`, `OFF` by default. +- `IOS_DEVELOPMENT_ROOT`, the path to `Developer` directory, can be explicitly set with your `/path/to/platform/Developer`. If left blank, PaddlePaddle will automatically pick the Xcode corresponding `platform`'s `Developer` directory based on your `IOS_PLATFORM` value. +- `IOS_SDK_ROOT`, the path to `SDK` root, can be explicitly set with your `/path/to/platform/Developer/SDKs/SDK`. if left black, PaddlePaddle will pick the latest SDK in the directory of `IOS_DEVELOPMENT_ROOT`. + +other settings： + +- `USE_EIGEN_FOR_BLAS`, whether to use Eigen for matrix computing. effective when `IOS_USE_VECLIB_FOR_BLAS=OFF`. Values can be `ON/OFF`, `OFF` by default. +- `HOST_C/CXX_COMPILER`, host C/C++ compiler. Uses value from environment variable `CC/CXX` by default or `cc/c++` if `CC/CXX` doesn't exist. + +some typical cmake configurations: + +```bash +cmake -DCMAKE_SYSTEM_NAME=iOS \ + -DIOS_PLATFORM=OS \ + -DIOS_ARCH="armv7;arm64" \ + -DIOS_ENABLE_BITCODE=ON \ + -DIOS_USE_VECLIB_FOR_BLAS=ON \ + -DCMAKE_INSTALL_PREFIX=your/path/to/install \ + -DWITH_C_API=ON \ + -DWITH_TESTING=OFF \ + -DWITH_SWIG_PY=OFF \ + .. +``` + +```bash +cmake -DCMAKE_SYSTEM_NAME=iOS \ + -DIOS_PLATFORM=SIMULATOR \ + -DIOS_ARCH="x86_64" \ + -DIOS_USE_VECLIB_FOR_BLAS=ON \ + -DCMAKE_INSTALL_PREFIX=your/path/to/install \ + -DWITH_C_API=ON \ + -DWITH_TESTING=OFF \ + -DWITH_SWIG_PY=OFF \ + .. +``` + +You can set other compiling parameters for your own need. I.E. if you are trying to minimize the library size, set `CMAKE_BUILD_TYPE` with `MinSizeRel`; or if the performance is your concern, set `CMAKE_BUILD_TYPE` with `Release`. You can even manipulate the PaddlePaddle compiling procedure by manually set `CMAKE_C/CXX_FLAGS` values. + +**TIPS for a better performance**: + +- set `CMAKE_BUILD_TYPE` with `Release` +- set `IOS_USE_VECLIB_FOR_BLAS` with `ON` + +## Compile and install + +After CMake, run following commands, PaddlePaddle will download the compile 3rd party dependencies, compile and install PaddlePaddle inference library. + +``` +$ make +$ make install +``` + +Please Note: if you compiled PaddlePaddle in the source directory for other platforms, do remove `third_party` and `build` directory within the source with `rm -rf` to ensure that all the 3rd party libraries dependencies and PaddlePaddle is newly compiled with current CMake configuration. + +`your/path/to/install` directory will have following directories after `compile` and `install`: + +- `include`, contains all the C-API header files. +- `lib`, contains PaddlePaddle C-API static library. +- `third_party` contains all the 3rd party libraries. + +Please note: if PaddlePaddle library need to support both physical devices and simulators, you will need to compile correspondingly, then merge fat library with `lipo`. + +Now you will have PaddlePaddle library compiled and installed, the fat library can be used in deep learning related iOS APPs. Please refer to C-API documentation for usage guides. diff --git a/doc/mobile/index_en.rst b/doc/mobile/index_en.rst index 3c08d736717cfe8d5fdf449dc58015086befbe60..ef421dacad458828cadf8cf505375d6c4bfd9dde 100644 --- a/doc/mobile/index_en.rst +++ b/doc/mobile/index_en.rst @@ -5,4 +5,5 @@ MOBILE :maxdepth: 1 cross_compiling_for_android_en.md + cross_compiling_for_ios_en.md cross_compiling_for_raspberry_en.md diff --git a/paddle/capi/error.cpp b/paddle/capi/error.cpp index 169b65f92104336d9ec12e2a5a6778db25080270..96ce31b45fc3f83237146443cbe4289af7bfa239 100644 --- a/paddle/capi/error.cpp +++ b/paddle/capi/error.cpp @@ -14,7 +14,7 @@ limitations under the License. */ #include "error.h" -const char* paddle_error_string(paddle_error err) { +extern "C" const char* paddle_error_string(paddle_error err) { switch (err) { case kPD_NULLPTR: return "nullptr error"; diff --git a/paddle/capi/error.h b/paddle/capi/error.h index 9d9d0ed63a5276c6b9a8747e1ee1fce6872bdc9e..2da9e0a3ef604fbcd53bac271c72ef33b3105152 100644 --- a/paddle/capi/error.h +++ b/paddle/capi/error.h @@ -29,9 +29,17 @@ typedef enum { kPD_UNDEFINED_ERROR = -1, } paddle_error; +#ifdef __cplusplus +extern "C" { +#endif + /** * Error string for Paddle API. */ PD_API const char* paddle_error_string(paddle_error err); +#ifdef __cplusplus +} +#endif + #endif diff --git a/paddle/framework/backward.cc b/paddle/framework/backward.cc index a17036c6527da3a4a32f021a57542b6b6d68a395..faf6e60cbd1bcda9864c12696b336998ea7606b7 100644 --- a/paddle/framework/backward.cc +++ b/paddle/framework/backward.cc @@ -430,14 +430,14 @@ std::vector> MakeBlockBackward( std::vector> op_grads; if ((*it)->Type() == "recurrent" || (*it)->Type() == "while") { - int step_block_idx = (*it)->GetBlockAttr("step_block"); + int step_block_idx = (*it)->GetBlockAttr("sub_block"); BlockDescBind* backward_block = CreateStepBlock( program_desc, no_grad_vars, grad_to_var, step_block_idx); op_grads = MakeOpGrad(*it, no_grad_vars, grad_to_var, {backward_block}); } else if ((*it)->Type() == "conditional_block") { BlockDescBind* backward_block = CreateStepBlock(program_desc, no_grad_vars, grad_to_var, - (*it)->GetBlockAttr("block")); + (*it)->GetBlockAttr("sub_block")); op_grads = MakeOpGrad(*it, no_grad_vars, grad_to_var, {backward_block}); } else { op_grads = MakeOpGrad(*it, no_grad_vars, grad_to_var); diff --git a/paddle/math/float16.h b/paddle/math/float16.h index 76ad3a01239e409caeefc36a3d562ed5e388dc92..efebbce50405018c6b7ce2049f8d55c33680469f 100644 --- a/paddle/math/float16.h +++ b/paddle/math/float16.h @@ -79,7 +79,7 @@ public: #ifdef PADDLE_CUDA_FP16 HOSTDEVICE inline explicit float16(const half& h) { #if CUDA_VERSION >= 9000 - x = reinterpret_cast<__half_raw*>(&h)->x; + x = reinterpret_cast<__half_raw*>(const_cast(&h))->x; #else x = h.x; #endif // CUDA_VERSION >= 9000 @@ -145,7 +145,7 @@ public: #ifdef PADDLE_CUDA_FP16 HOSTDEVICE inline float16& operator=(const half& rhs) { #if CUDA_VERSION >= 9000 - x = reinterpret_cast<__half_raw*>(&rhs)->x; + x = reinterpret_cast<__half_raw*>(const_cast(&rhs))->x; #else x = rhs.x; #endif diff --git a/paddle/math/tests/test_matrixCompare.cpp b/paddle/math/tests/test_matrixCompare.cpp index 7e5a1db44a5302e3b4e5d2768755824666e880ba..afb8d9d599b15a0b6d19b7ecca5e91b623695dea 100644 --- a/paddle/math/tests/test_matrixCompare.cpp +++ b/paddle/math/tests/test_matrixCompare.cpp @@ -244,7 +244,7 @@ TEST(Matrix, unary) { LOG(WARNING) << "This version of PaddlePaddle was not built with LAPACK" << "support so we cannot test matrix inverse. To test " << "matrix inverse, please install LAPACKE " - << "and MKL/Openblas/ATLAS, and re-build PaddlePaddle."; + << "and MKL/Openblas, and re-build PaddlePaddle."; #endif } } diff --git a/paddle/operators/cast_op.cc b/paddle/operators/cast_op.cc index 42bff69a1e1c051354296d2e2426e1658792a94d..d641b8fc9fea81d1e364ae05de98ed7760a32648 100644 --- a/paddle/operators/cast_op.cc +++ b/paddle/operators/cast_op.cc @@ -74,4 +74,5 @@ REGISTER_OP_WITH_KERNEL(cast, ops::CastOpGradMaker, ops::CastOpInferShape, REGISTER_OP_CPU_KERNEL(cast, ops::CastOpKernel, ops::CastOpKernel, ops::CastOpKernel, - ops::CastOpKernel); + ops::CastOpKernel, + ops::CastOpKernel); diff --git a/paddle/operators/cast_op.cu b/paddle/operators/cast_op.cu index 4681deaa62fdcde18f39f4192841be66f49d7c08..91e6fb391c637cc0d70a401d8d834451059ef6df 100644 --- a/paddle/operators/cast_op.cu +++ b/paddle/operators/cast_op.cu @@ -19,4 +19,5 @@ using CastOpKernel = paddle::operators::CastOpKernel; REGISTER_OP_CUDA_KERNEL(cast, CastOpKernel, CastOpKernel, - CastOpKernel, CastOpKernel); + CastOpKernel, CastOpKernel, + CastOpKernel); diff --git a/paddle/operators/chunk_eval_op.cc b/paddle/operators/chunk_eval_op.cc index 94127ab33e51d5529b63b5e3696032ef8adcf03e..894f355deb9d764ef72d452f362e6b42f8831667 100644 --- a/paddle/operators/chunk_eval_op.cc +++ b/paddle/operators/chunk_eval_op.cc @@ -32,6 +32,13 @@ class ChunkEvalOp : public framework::OperatorWithKernel { "Output(Recall) of ChunkEvalOp should not be null."); PADDLE_ENFORCE(ctx->HasOutput("F1-Score"), "Output(F1-Score) of ChunkEvalOp should not be null."); + PADDLE_ENFORCE(ctx->HasOutput("NumInferChunks"), + "Output(NumInferChunks) of ChunkEvalOp should not be null."); + PADDLE_ENFORCE(ctx->HasOutput("NumLabelChunks"), + "Output(NumLabelChunks) of ChunkEvalOp should not be null."); + PADDLE_ENFORCE( + ctx->HasOutput("NumCorrectChunks"), + "Output(NumCorrectChunks) of ChunkEvalOp should not be null."); auto inference_dim = ctx->GetInputDim("Inference"); auto label_dim = ctx->GetInputDim("Label"); @@ -42,6 +49,9 @@ class ChunkEvalOp : public framework::OperatorWithKernel { ctx->SetOutputDim("Precision", {1}); ctx->SetOutputDim("Recall", {1}); ctx->SetOutputDim("F1-Score", {1}); + ctx->SetOutputDim("NumInferChunks", {1}); + ctx->SetOutputDim("NumLabelChunks", {1}); + ctx->SetOutputDim("NumCorrectChunks", {1}); } protected: @@ -70,6 +80,16 @@ class ChunkEvalOpMaker : public framework::OpProtoAndCheckerMaker { "sensitivity) of chunks on the given mini-batch."); AddOutput("F1-Score", "(float). The evaluated F1-Score on the given mini-batch."); + AddOutput("NumInferChunks", + "(int64_t). The number of chunks in Inference on the given " + "mini-batch."); + AddOutput( + "NumLabelChunks", + "(int64_t). The number of chunks in Label on the given mini-batch."); + AddOutput( + "NumCorrectChunks", + "(int64_t). The number of chunks both in Inference and Label on the " + "given mini-batch."); AddAttr("num_chunk_types", "(int). The number of chunk type. See below for details."); AddAttr( diff --git a/paddle/operators/chunk_eval_op.h b/paddle/operators/chunk_eval_op.h index 9cd758a8253914515437b480e17a94d5d6b21fd2..74ab435c860b22b2ee3f485743540976a7a31b96 100644 --- a/paddle/operators/chunk_eval_op.h +++ b/paddle/operators/chunk_eval_op.h @@ -111,9 +111,7 @@ class ChunkEvalKernel : public framework::OpKernel { std::vector label_segments; std::vector output_segments; std::set excluded_chunk_types; - int64_t num_output_segments = 0; - int64_t num_label_segments = 0; - int64_t num_correct = 0; + if (context.Attr("chunk_scheme") == "IOB") { num_tag_types = 2; tag_begin = 0; @@ -151,12 +149,24 @@ class ChunkEvalKernel : public framework::OpKernel { auto* precision = context.Output("Precision"); auto* recall = context.Output("Recall"); auto* f1 = context.Output("F1-Score"); + auto* num_infer_chunks = context.Output("NumInferChunks"); + auto* num_label_chunks = context.Output("NumLabelChunks"); + auto* num_correct_chunks = context.Output("NumCorrectChunks"); const int64_t* inference_data = inference->data(); const int64_t* label_data = label->data(); T* precision_data = precision->mutable_data(context.GetPlace()); T* racall_data = recall->mutable_data(context.GetPlace()); T* f1_data = f1->mutable_data(context.GetPlace()); + int64_t* num_infer_chunks_data = + num_infer_chunks->mutable_data(context.GetPlace()); + int64_t* num_label_chunks_data = + num_label_chunks->mutable_data(context.GetPlace()); + int64_t* num_correct_chunks_data = + num_correct_chunks->mutable_data(context.GetPlace()); + *num_infer_chunks_data = 0; + *num_label_chunks_data = 0; + *num_correct_chunks_data = 0; auto lod = label->lod(); PADDLE_ENFORCE_EQ(lod.size(), 1UL, "Only support one level sequence now."); @@ -166,17 +176,23 @@ class ChunkEvalKernel : public framework::OpKernel { for (int i = 0; i < num_sequences; ++i) { int seq_length = lod[0][i + 1] - lod[0][i]; EvalOneSeq(inference_data + lod[0][i], label_data + lod[0][i], seq_length, - output_segments, label_segments, num_output_segments, - num_label_segments, num_correct, num_chunk_types, - num_tag_types, other_chunk_type, tag_begin, tag_inside, - tag_end, tag_single, excluded_chunk_types); + output_segments, label_segments, *num_infer_chunks_data, + *num_label_chunks_data, *num_correct_chunks_data, + num_chunk_types, num_tag_types, other_chunk_type, tag_begin, + tag_inside, tag_end, tag_single, excluded_chunk_types); } - *precision_data = !num_output_segments ? 0 : static_cast(num_correct) / - num_output_segments; - *racall_data = !num_label_segments ? 0 : static_cast(num_correct) / - num_label_segments; - *f1_data = !num_correct ? 0 : 2 * (*precision_data) * (*racall_data) / - ((*precision_data) + (*racall_data)); + *precision_data = !(*num_infer_chunks_data) + ? 0 + : static_cast(*num_correct_chunks_data) / + (*num_infer_chunks_data); + *racall_data = !(*num_label_chunks_data) + ? 0 + : static_cast(*num_correct_chunks_data) / + (*num_label_chunks_data); + *f1_data = !(*num_correct_chunks_data) + ? 0 + : 2 * (*precision_data) * (*racall_data) / + ((*precision_data) + (*racall_data)); } void EvalOneSeq(const int64_t* output, const int64_t* label, int length, diff --git a/paddle/operators/conditional_block_op.cc b/paddle/operators/conditional_block_op.cc index 03c58a7eab8b2071a3a0b75ac0c665e32ef39876..6f2ef9174e84a0c0ae096956c04039435e6583c6 100644 --- a/paddle/operators/conditional_block_op.cc +++ b/paddle/operators/conditional_block_op.cc @@ -65,7 +65,7 @@ class ConditionalBlockOp : public ConditionalOp { scopes->front() = &scope.NewScope(); auto &cur_scope = *scopes->front(); - auto *block = Attr("block"); + auto *block = Attr("sub_block"); framework::Executor exec(dev_ctx); exec.Run(*block->Program(), &cur_scope, block->ID(), false); } @@ -88,7 +88,7 @@ class ConditionalBlockOpProtoMaker : public framework::OpProtoAndCheckerMaker { "unify the conditional block, rnn and while op, the type of " "scope is std::vector"); AddAttr( - "block", "The step block of conditional block operator"); + "sub_block", "The step block of conditional block operator"); AddComment(R"DOC(Conditional block operator Run the sub-block if X is not empty. Params is the other inputs and Out is the @@ -117,7 +117,7 @@ class ConditionalBlockGradOp : public ConditionalOp { auto &scopes = scope_var->Get>(); framework::Scope &cur_scope = *scopes[0]; - auto *block = Attr("block"); + auto *block = Attr("sub_block"); framework::Executor exec(dev_ctx); exec.Run(*block->Program(), &cur_scope, block->ID(), false); @@ -181,7 +181,7 @@ class ConditionalBlockGradMaker : public framework::SingleGradOpDescMaker { grad_op->SetInput("Scope", Output("Scope")); grad_op->SetOutput(framework::GradVarName("X"), InputGrad("X")); grad_op->SetOutput(framework::GradVarName("Params"), InputGrad("Params")); - grad_op->SetBlockAttr("block", *this->grad_block_[0]); + grad_op->SetBlockAttr("sub_block", *this->grad_block_[0]); return std::unique_ptr(grad_op); } }; diff --git a/paddle/operators/conv_op.h b/paddle/operators/conv_op.h index 749258183ba058cf0ed8d91c4406813694314b85..d2de4e80f751d4938ac9cad60871b470fccf225c 100644 --- a/paddle/operators/conv_op.h +++ b/paddle/operators/conv_op.h @@ -261,8 +261,12 @@ class GemmConvGradKernel : public framework::OpKernel { if (input_grad) { input_grad->mutable_data(context.GetPlace()); - set_zero(dev_ctx, input_grad, static_cast(0)); + // if is_expand is false, the operation of set_zero is unnecessary, + // because math::matmul will reset input_grad. + if (is_expand) { + set_zero(dev_ctx, input_grad, static_cast(0)); + } math::Col2VolFunctor col2vol; math::Col2ImFunctor col2im; diff --git a/paddle/operators/conv_transpose_op.h b/paddle/operators/conv_transpose_op.h index 80600b53614994ba0c740aed0d75c9944333fecc..1171b0435fd2b1abe541043e8283a8fc09dc13c7 100644 --- a/paddle/operators/conv_transpose_op.h +++ b/paddle/operators/conv_transpose_op.h @@ -225,7 +225,6 @@ class GemmConvTransposeGradKernel : public framework::OpKernel { if (input_grad) { input_grad->mutable_data(context.GetPlace()); - set_zero(dev_ctx, input_grad, static_cast(0)); } if (filter_grad) { // filter size (m, c, k_h, k_w) filter_grad->mutable_data(context.GetPlace()); diff --git a/paddle/operators/math/math_function.cc b/paddle/operators/math/math_function.cc index 2b35e4532a9c9f72f473020d472244234af24248..a05810d7781f5286e70b53005ef0b193c945c54c 100644 --- a/paddle/operators/math/math_function.cc +++ b/paddle/operators/math/math_function.cc @@ -277,6 +277,14 @@ void set_constant_with_place( TensorSetConstantCPU(tensor, value)); } +template <> +void set_constant_with_place( + const platform::DeviceContext& context, framework::Tensor* tensor, + float value) { + framework::VisitDataType(framework::ToDataType(tensor->type()), + TensorSetConstantCPU(tensor, value)); +} + struct TensorSetConstantWithPlace : public boost::static_visitor { TensorSetConstantWithPlace(const platform::DeviceContext& context, framework::Tensor* tensor, float value) diff --git a/paddle/operators/math/math_function.cu b/paddle/operators/math/math_function.cu index 1b560a7e2d29c1b63a25d4ec9bbd82d5960a279d..e33070c40fbfa7f2794426247ef77b8fcaee4ec6 100644 --- a/paddle/operators/math/math_function.cu +++ b/paddle/operators/math/math_function.cu @@ -273,6 +273,13 @@ void set_constant_with_place( TensorSetConstantGPU(context, tensor, value)); } +template <> +void set_constant_with_place( + const platform::DeviceContext& context, framework::Tensor* tensor, + float value) { + set_constant_with_place(context, tensor, value); +} + template struct RowwiseAdd; template struct RowwiseAdd; template struct ColwiseSum; diff --git a/paddle/operators/recurrent_op.cc b/paddle/operators/recurrent_op.cc index 29f91636438449f90ea3ffee8adc21595aabe202..232d926f7b975c3b8ebecad983d0f1cc54b9486f 100644 --- a/paddle/operators/recurrent_op.cc +++ b/paddle/operators/recurrent_op.cc @@ -25,7 +25,7 @@ constexpr char kOutputs[] = "outputs"; constexpr char kStepScopes[] = "step_scopes"; constexpr char kExStates[] = "ex_states"; constexpr char kStates[] = "states"; -constexpr char kStepBlock[] = "step_block"; +constexpr char kStepBlock[] = "sub_block"; constexpr char kReverse[] = "reverse"; constexpr char kIsTrain[] = "is_train"; #define GRAD_SUFFIX "@GRAD" diff --git a/paddle/operators/reduce_op.cc b/paddle/operators/reduce_op.cc index b754637bf29225615f129d7423d60518e053ca18..fedc2a5c37ff84ffdf8ebd2f19296db92e256e5b 100644 --- a/paddle/operators/reduce_op.cc +++ b/paddle/operators/reduce_op.cc @@ -37,18 +37,23 @@ class ReduceOp : public framework::OperatorWithKernel { PADDLE_ENFORCE_LT( dim, x_rank, "The dim should be in the range [-rank(input), rank(input))."); - bool keep_dim = ctx->Attrs().Get("keep_dim"); - auto dims_vector = vectorize(x_dims); - if (keep_dim || x_rank == 1) { - dims_vector[dim] = 1; + bool reduce_all = ctx->Attrs().Get("reduce_all"); + if (reduce_all) { + ctx->SetOutputDim("Out", {1}); } else { - dims_vector.erase(dims_vector.begin() + dim); - } - auto out_dims = framework::make_ddim(dims_vector); - ctx->SetOutputDim("Out", out_dims); - if (dim != 0) { - // Only pass LoD when not reducing on the first dim. - ctx->ShareLoD("X", /*->*/ "Out"); + bool keep_dim = ctx->Attrs().Get("keep_dim"); + auto dims_vector = vectorize(x_dims); + if (keep_dim || x_rank == 1) { + dims_vector[dim] = 1; + } else { + dims_vector.erase(dims_vector.begin() + dim); + } + auto out_dims = framework::make_ddim(dims_vector); + ctx->SetOutputDim("Out", out_dims); + if (dim != 0) { + // Only pass LoD when not reducing on the first dim. + ctx->ShareLoD("X", /*->*/ "Out"); + } } } }; @@ -95,11 +100,16 @@ class ReduceOpMaker : public framework::OpProtoAndCheckerMaker { "(bool, default false) " "If true, retain the reduced dimension with length 1.") .SetDefault(false); + AddAttr("reduce_all", + "(bool, default false) " + "If true, output a scalar reduced along all dimensions.") + .SetDefault(false); comment_ = R"DOC( {ReduceOp} Operator. This operator computes the {reduce} of input tensor along the given dimension. The result tensor has 1 fewer dimension than the input unless keep_dim is true. +If reduce_all is true, just reduce along all dimensions and output a scalar. )DOC"; AddComment(comment_); diff --git a/paddle/operators/reduce_op.h b/paddle/operators/reduce_op.h index 47ce910f2821467c701a7f5e22a8dbe5c8c95c92..7bd99cb1e6d532963ef648202f460f363baad9b5 100644 --- a/paddle/operators/reduce_op.h +++ b/paddle/operators/reduce_op.h @@ -26,10 +26,12 @@ using DDim = framework::DDim; template using EigenTensor = framework::EigenTensor; - template using EigenScalar = framework::EigenScalar; +template +using EigenVector = framework::EigenVector; struct SumFunctor { template @@ -95,26 +97,41 @@ template class ReduceKernel : public framework::OpKernel { public: void Compute(const framework::ExecutionContext& context) const override { - int rank = context.Input("X")->dims().size(); - switch (rank) { - case 1: - ReduceCompute<1>(context); - break; - case 2: - ReduceCompute<2>(context); - break; - case 3: - ReduceCompute<3>(context); - break; - case 4: - ReduceCompute<4>(context); - break; - case 5: - ReduceCompute<5>(context); - break; - case 6: - ReduceCompute<6>(context); - break; + bool reduce_all = context.Attr("reduce_all"); + if (reduce_all) { + // Flatten and reduce 1-D tensor + auto* input = context.Input("X"); + auto* output = context.Output("Out"); + output->mutable_data(context.GetPlace()); + auto x = EigenVector::Flatten(*input); + auto out = EigenScalar::From(*output); + auto& place = + *context.template device_context().eigen_device(); + auto reduce_dim = Eigen::array({{0}}); + Functor functor; + functor(place, x, out, reduce_dim); + } else { + int rank = context.Input("X")->dims().size(); + switch (rank) { + case 1: + ReduceCompute<1>(context); + break; + case 2: + ReduceCompute<2>(context); + break; + case 3: + ReduceCompute<3>(context); + break; + case 4: + ReduceCompute<4>(context); + break; + case 5: + ReduceCompute<5>(context); + break; + case 6: + ReduceCompute<6>(context); + break; + } } } @@ -157,26 +174,46 @@ template class ReduceGradKernel : public framework::OpKernel { public: void Compute(const framework::ExecutionContext& context) const override { - int rank = context.Input("X")->dims().size(); - switch (rank) { - case 1: - ReduceGradCompute<1>(context); - break; - case 2: - ReduceGradCompute<2>(context); - break; - case 3: - ReduceGradCompute<3>(context); - break; - case 4: - ReduceGradCompute<4>(context); - break; - case 5: - ReduceGradCompute<5>(context); - break; - case 6: - ReduceGradCompute<6>(context); - break; + bool reduce_all = context.Attr("reduce_all"); + if (reduce_all) { + auto* input0 = context.Input("X"); + auto* input1 = context.Input("Out"); + auto* input2 = context.Input(framework::GradVarName("Out")); + auto* output = context.Output(framework::GradVarName("X")); + output->mutable_data(context.GetPlace()); + auto x = EigenVector::Flatten(*input0); + auto x_reduce = EigenVector::From(*input1); + auto x_reduce_grad = EigenVector::From(*input2); + auto x_grad = EigenVector::Flatten(*output); + auto& place = + *context.template device_context().eigen_device(); + auto broadcast_dim = + Eigen::array({{static_cast(input0->numel())}}); + Functor functor; + functor(place, x, x_reduce, x_grad, x_reduce_grad, broadcast_dim, + broadcast_dim[0]); + } else { + int rank = context.Input("X")->dims().size(); + switch (rank) { + case 1: + ReduceGradCompute<1>(context); + break; + case 2: + ReduceGradCompute<2>(context); + break; + case 3: + ReduceGradCompute<3>(context); + break; + case 4: + ReduceGradCompute<4>(context); + break; + case 5: + ReduceGradCompute<5>(context); + break; + case 6: + ReduceGradCompute<6>(context); + break; + } } } diff --git a/paddle/operators/reshape_op.cc b/paddle/operators/reshape_op.cc index 164f3104eb69caf4f93542de39c3d089694ffe03..5baf45953645719c4aca2191f54ea7de7aa3ca3e 100644 --- a/paddle/operators/reshape_op.cc +++ b/paddle/operators/reshape_op.cc @@ -94,9 +94,9 @@ Given a 2-D tensor X with 2 rows and 2 columns [[1, 2], [3, 4]] and target shape = [1, 4], the reshape operator will transform -the tensor X into a 1-D tensor: +the tensor X into a 2-D tensor: - [1, 2, 3, 4] + [[1, 2, 3, 4]] One dimension in the target shape can be set -1, and the real dimension will be infered from the original shape of Input(X) and other diff --git a/paddle/operators/while_op.cc b/paddle/operators/while_op.cc index b8e44bcc5a99380fdf08cc2819b20045695eaf87..9a092a570ff1f3f529413cd44dff55147adbaadc 100644 --- a/paddle/operators/while_op.cc +++ b/paddle/operators/while_op.cc @@ -25,7 +25,7 @@ namespace operators { using StepScopeVar = std::vector; using LoDTensor = framework::LoDTensor; -constexpr char kStepBlock[] = "step_block"; +constexpr char kStepBlock[] = "sub_block"; constexpr char kCondition[] = "Condition"; constexpr char kStepScopes[] = "StepScopes"; constexpr char kParameters[] = "X"; diff --git a/paddle/platform/device_context.cc b/paddle/platform/device_context.cc index 2c7f96421621b9a34d1ec96c13d9c354a0d4012c..1c72b5055971e73c7aa560a61ca9d3c48dc56fbc 100644 --- a/paddle/platform/device_context.cc +++ b/paddle/platform/device_context.cc @@ -125,6 +125,22 @@ cudnnHandle_t CUDADeviceContext::cudnn_handle() const { return cudnn_handle_; } cudaStream_t CUDADeviceContext::stream() const { return stream_; } +CudnnDeviceContext::CudnnDeviceContext(CudnnPlace place) + : CUDADeviceContext(place), place_(place) { + PADDLE_ENFORCE(dynload::cudnnCreate(&cudnn_handle_)); + PADDLE_ENFORCE(dynload::cudnnSetStream(cudnn_handle_, stream())); +} + +CudnnDeviceContext::~CudnnDeviceContext() { + SetDeviceId(place_.device); + Wait(); + PADDLE_ENFORCE(dynload::cudnnDestroy(cudnn_handle_)); +} + +Place CudnnDeviceContext::GetPlace() const { return CudnnPlace(); } + +cudnnHandle_t CudnnDeviceContext::cudnn_handle() const { return cudnn_handle_; } + #endif } // namespace platform diff --git a/paddle/platform/device_context.h b/paddle/platform/device_context.h index 596d9d0bba420a47fc10cc9dd96a755daa35dbac..f67194993db1f4160bd6894b2c845a82f4da2354 100644 --- a/paddle/platform/device_context.h +++ b/paddle/platform/device_context.h @@ -86,6 +86,22 @@ class CUDADeviceContext : public DeviceContext { cublasHandle_t cublas_handle_; }; +class CudnnDeviceContext : public CUDADeviceContext { + public: + explicit CudnnDeviceContext(CudnnPlace place); + virtual ~CudnnDeviceContext(); + + /*! \brief Return place in the device context. */ + Place GetPlace() const final; + + /*! \brief Return cudnn handle in the device context. */ + cudnnHandle_t cudnn_handle() const; + + private: + cudnnHandle_t cudnn_handle_; + CudnnPlace place_; +}; + #endif } // namespace platform diff --git a/paddle/platform/device_context_test.cc b/paddle/platform/device_context_test.cc index 4893cd92f6a74f7992c279ebd51232049f29e853..be3b2af5af09cb18f5156412ff60a7fc15a16487 100644 --- a/paddle/platform/device_context_test.cc +++ b/paddle/platform/device_context_test.cc @@ -46,3 +46,19 @@ TEST(Device, CUDADeviceContext) { delete device_context; } } + +TEST(Device, CudnnDeviceContext) { + using paddle::platform::CudnnDeviceContext; + using paddle::platform::CudnnPlace; + if (paddle::platform::dynload::HasCUDNN()) { + int count = paddle::platform::GetCUDADeviceCount(); + for (int i = 0; i < count; ++i) { + CudnnDeviceContext* device_context = + new CudnnDeviceContext(CudnnPlace(i)); + cudnnHandle_t cudnn_handle = device_context->cudnn_handle(); + ASSERT_NE(nullptr, cudnn_handle); + ASSERT_NE(nullptr, device_context->stream()); + delete device_context; + } + } +} diff --git a/paddle/platform/dynload/nccl.cc b/paddle/platform/dynload/nccl.cc index 8f92b8d94d56047b7d3fb43b15e3c06575c8d57b..91168f37effff3f8b864b6bb2ede070cb0a976fa 100644 --- a/paddle/platform/dynload/nccl.cc +++ b/paddle/platform/dynload/nccl.cc @@ -25,6 +25,11 @@ void *nccl_dso_handle; NCCL_RAND_ROUTINE_EACH(DEFINE_WRAP); +void LoadNCCLDSO() { + platform::call_once(nccl_dso_flag, + [] { GetNCCLDsoHandle(&nccl_dso_handle); }); +} + } // namespace dynload } // namespace platform } // namespace paddle diff --git a/paddle/platform/dynload/nccl.h b/paddle/platform/dynload/nccl.h index 981b2ab258a34ce92f02ee12b5957f88ba61d1c0..11007c1031c6d224c475e9ef4f11e7797decd78e 100644 --- a/paddle/platform/dynload/nccl.h +++ b/paddle/platform/dynload/nccl.h @@ -28,18 +28,18 @@ extern std::once_flag nccl_dso_flag; extern void* nccl_dso_handle; #ifdef PADDLE_USE_DSO -#define DECLARE_DYNAMIC_LOAD_NCCL_WRAP(__name) \ - struct DynLoad__##__name { \ - template \ - auto operator()(Args... args) -> decltype(__name(args...)) { \ - using nccl_func = decltype(__name(args...)) (*)(Args...); \ - platform::call_once(nccl_dso_flag, \ - paddle::platform::dynload::GetNCCLDsoHandle, \ - &nccl_dso_handle); \ - void* p_##__name = dlsym(nccl_dso_handle, #__name); \ - return reinterpret_cast(p_##__name)(args...); \ - } \ - }; \ +extern void LoadNCCLDSO(); + +#define DECLARE_DYNAMIC_LOAD_NCCL_WRAP(__name) \ + struct DynLoad__##__name { \ + template \ + auto operator()(Args... args) -> decltype(__name(args...)) { \ + using nccl_func = decltype(__name(args...)) (*)(Args...); \ + paddle::platform::dynload::LoadNCCLDSO(); \ + void* p_##__name = dlsym(nccl_dso_handle, #__name); \ + return reinterpret_cast(p_##__name)(args...); \ + } \ + }; \ extern DynLoad__##__name __name #else #define DECLARE_DYNAMIC_LOAD_NCCL_WRAP(__name) \ diff --git a/paddle/platform/nccl_test.cu b/paddle/platform/nccl_test.cu index c99dae68bef67c58d3efea42fef45e84bb3d9255..94ab360a1967d22e73bc6aefc0301487537c97f7 100644 --- a/paddle/platform/nccl_test.cu +++ b/paddle/platform/nccl_test.cu @@ -31,7 +31,7 @@ namespace platform { TEST(NCCL, init) { std::vector comms; comms.resize(dev_count); - PADDLE_ENFORCE(dynload::ncclCommInitAll(comms.data(), dev_count, nullptr)); + dynload::ncclCommInitAll(comms.data(), dev_count, nullptr); for (int i = 0; i < dev_count; ++i) { dynload::ncclCommDestroy(comms[i]); } @@ -62,7 +62,7 @@ TEST(NCCL, all_reduce) { std::vector comms; comms.resize(dev_count); VLOG(1) << "Initializing ncclComm"; - PADDLE_ENFORCE(dynload::ncclCommInitAll(comms.data(), dev_count, nullptr)); + dynload::ncclCommInitAll(comms.data(), dev_count, nullptr); VLOG(1) << "ncclComm initialized"; VLOG(1) << "Creating thread data"; std::vector>> data; diff --git a/paddle/platform/place.cc b/paddle/platform/place.cc index 856e54df89c1c18ade040957188a2fbda0901473..25fe8d21b49b07a6afe2938245906dc1bdd90398 100644 --- a/paddle/platform/place.cc +++ b/paddle/platform/place.cc @@ -23,6 +23,7 @@ class PlacePrinter : public boost::static_visitor<> { public: explicit PlacePrinter(std::ostream &os) : os_(os) {} void operator()(const CPUPlace &) { os_ << "CPUPlace"; } + void operator()(const MKLDNNPlace &) { os_ << "MKLDNNPlace"; } void operator()(const GPUPlace &p) { os_ << "GPUPlace(" << p.device << ")"; } private: @@ -38,12 +39,17 @@ const Place &get_place() { return the_default_place; } const GPUPlace default_gpu() { return GPUPlace(0); } const CPUPlace default_cpu() { return CPUPlace(); } +const MKLDNNPlace default_mkldnn() { return MKLDNNPlace(); } bool is_gpu_place(const Place &p) { return boost::apply_visitor(IsGPUPlace(), p); } bool is_cpu_place(const Place &p) { - return !boost::apply_visitor(IsGPUPlace(), p); + return !is_gpu_place(p) && !is_mkldnn_place(p); +} + +bool is_mkldnn_place(const Place &p) { + return boost::apply_visitor(IsMKLDNNPlace(), p); } bool places_are_same_class(const Place &p1, const Place &p2) { diff --git a/paddle/platform/place.h b/paddle/platform/place.h index 5370360a7de26e409a1545182a12d3df1f37658b..4526945792b2ea96cc4e9df11d8f35897cba7526 100644 --- a/paddle/platform/place.h +++ b/paddle/platform/place.h @@ -31,6 +31,14 @@ struct CPUPlace { inline bool operator!=(const CPUPlace &) const { return false; } }; +struct MKLDNNPlace { + MKLDNNPlace() {} + + // needed for variant equality comparison + inline bool operator==(const MKLDNNPlace &) const { return true; } + inline bool operator!=(const MKLDNNPlace &) const { return false; } +}; + struct GPUPlace { GPUPlace() : GPUPlace(0) {} explicit GPUPlace(int d) : device(d) {} @@ -43,16 +51,28 @@ struct GPUPlace { int device; }; +struct CudnnPlace : public GPUPlace { + CudnnPlace() : GPUPlace() {} + explicit CudnnPlace(int d) : GPUPlace(d) {} +}; + struct IsGPUPlace : public boost::static_visitor { bool operator()(const CPUPlace &) const { return false; } + bool operator()(const MKLDNNPlace &) const { return false; } bool operator()(const GPUPlace &gpu) const { return true; } }; +struct IsMKLDNNPlace : public boost::static_visitor { + bool operator()(const MKLDNNPlace &) const { return true; } + bool operator()(const CPUPlace &) const { return false; } + bool operator()(const GPUPlace &) const { return false; } +}; + // Define the max number of Place in bit length. i.e., the max number of places // should be less equal than 2^(NUM_PLACE_TYPE_LIMIT_IN_BIT) #define NUM_PLACE_TYPE_LIMIT_IN_BIT 4 -typedef boost::variant Place; +typedef boost::variant Place; // static check number of place types is less equal than // 2^(NUM_PLACE_TYPE_LIMIT_IN_BIT) @@ -65,9 +85,11 @@ const Place &get_place(); const GPUPlace default_gpu(); const CPUPlace default_cpu(); +const MKLDNNPlace default_mkldnn(); bool is_gpu_place(const Place &); bool is_cpu_place(const Place &); +bool is_mkldnn_place(const Place &); bool places_are_same_class(const Place &, const Place &); std::ostream &operator<<(std::ostream &, const Place &); diff --git a/paddle/platform/place_test.cc b/paddle/platform/place_test.cc index 33e2e5a439ce6801c02daba4bcbd462a74d7a614..184af12c230f1ccd7826e507f16f4e91ca380a45 100644 --- a/paddle/platform/place_test.cc +++ b/paddle/platform/place_test.cc @@ -21,9 +21,15 @@ TEST(Place, Default) { EXPECT_TRUE(paddle::platform::is_gpu_place(paddle::platform::get_place())); EXPECT_TRUE(paddle::platform::is_gpu_place(paddle::platform::default_gpu())); EXPECT_TRUE(paddle::platform::is_cpu_place(paddle::platform::default_cpu())); + EXPECT_TRUE( + paddle::platform::is_mkldnn_place(paddle::platform::default_mkldnn())); paddle::platform::set_place(paddle::platform::CPUPlace()); EXPECT_TRUE(paddle::platform::is_cpu_place(paddle::platform::get_place())); + + paddle::platform::set_place(paddle::platform::MKLDNNPlace()); + EXPECT_FALSE(paddle::platform::is_cpu_place(paddle::platform::get_place())); + EXPECT_TRUE(paddle::platform::is_mkldnn_place(paddle::platform::get_place())); } TEST(Place, Print) { diff --git a/paddle/platform/variant.h b/paddle/platform/variant.h index 619897ca19eb2e6f4dbfd9160edf8c4bc58c89a9..284b4c42ac068b23737c12d3f147bbceb135dacc 100644 --- a/paddle/platform/variant.h +++ b/paddle/platform/variant.h @@ -14,6 +14,19 @@ #pragma once +#ifdef __CUDACC__ +#ifdef __CUDACC_VER_MAJOR__ +// CUDA 9 define `__CUDACC_VER__` as a warning message, manually define +// __CUDACC_VER__ instead. +#undef __CUDACC_VER__ + +#define __CUDACC_VER__ \ + (__CUDACC_VER_MAJOR__ * 10000 + __CUDACC_VER_MINOR__ * 100 + \ + __CUDACC_VER_BUILD__) +#endif + +#endif + #include #ifdef PADDLE_WITH_CUDA diff --git a/paddle/pybind/pybind.cc b/paddle/pybind/pybind.cc index c16d3e0cbe01f90a5aa9a5d7a523cd4e282e4771..1faf24bcb8828596ec37abde9e699f46526e41df 100644 --- a/paddle/pybind/pybind.cc +++ b/paddle/pybind/pybind.cc @@ -282,6 +282,23 @@ All parameter, weight, gradient are variables in Paddle. } return ret_values; }); + m.def("get_grad_op_descs", + [](const OpDescBind &op_desc, + const std::unordered_set &no_grad_set, + std::unordered_map &grad_to_var, + const std::vector &grad_sub_block) { + std::vector> grad_op_descs = + framework::OpInfoMap::Instance() + .Get(op_desc.Type()) + .GradOpMaker()(op_desc, no_grad_set, &grad_to_var, + grad_sub_block); + std::vector grad_op_desc_ptrs(grad_op_descs.size()); + std::transform( + grad_op_descs.begin(), grad_op_descs.end(), + grad_op_desc_ptrs.begin(), + [](std::unique_ptr &p) { return p.release(); }); + return grad_op_desc_ptrs; + }); m.def("prune", [](const ProgramDescBind &origin, const std::vector> &targets) { ProgramDescBind prog_with_targets(origin); diff --git a/paddle/scripts/cluster_train_v2/openmpi/docker_cluster/Dockerfile b/paddle/scripts/cluster_train_v2/openmpi/docker_cluster/Dockerfile index 1a2d19e823541750830fcaa25f65b2f8e1ea2b49..c2f631bdf4ed52a5dfa3fbcf1157d0abbdeadb9b 100644 --- a/paddle/scripts/cluster_train_v2/openmpi/docker_cluster/Dockerfile +++ b/paddle/scripts/cluster_train_v2/openmpi/docker_cluster/Dockerfile @@ -1,7 +1,7 @@ # Build this image: docker build -t mpi . # -FROM paddledev/paddle:0.10.0rc3 +FROM paddlepaddle/paddle:0.10.0rc3 ENV DEBIAN_FRONTEND noninteractive diff --git a/paddle/scripts/docker/README.md b/paddle/scripts/docker/README.md index f3a6f1dba7588c6b29c1dcae26ec134c1a7f937d..f0620498cfa6775ce2949cc02fa9f6c9529dec2e 100644 --- a/paddle/scripts/docker/README.md +++ b/paddle/scripts/docker/README.md @@ -20,7 +20,7 @@ binaries. ## Run The Build -### Build Evironments +### Build Environments The pre-built build environment images are: @@ -192,7 +192,7 @@ For developers who are interested in the C++ source code, please use -e "WOBOQ=O - The following command builds PaddlePaddle, generates HTML pages from C++ source code, and writes HTML pages into `$HOME/woboq_out` on the host: ```bash -docker run -v $PWD:/paddle -v $HOME/woboq_out:/woboq_out -e "WITH_GPU=OFF" -e "WITH_AVX=ON" -e "WITH_TEST=ON" -e "WOBOQ=ON" paddlepaddle/paddle:latest-dev +docker run -v $PWD:/paddle -v $HOME/woboq_out:/woboq_out -e "WITH_GPU=OFF" -e "WITH_AVX=ON" -e "WITH_TESTING=ON" -e "WOBOQ=ON" paddlepaddle/paddle:latest-dev ``` - You can open the generated HTML files in your Web browser. Or, if you want to run a Nginx container to serve them for a wider audience, you can run: diff --git a/paddle/scripts/tools/build_docs/build_docs.sh b/paddle/scripts/tools/build_docs/build_docs.sh index c6cbbc4eef94fb2e2fc3c1ce71734fbb23fc22d7..f9bc8bf63ae9afdfca1ff660bc83e62e71f03005 100755 --- a/paddle/scripts/tools/build_docs/build_docs.sh +++ b/paddle/scripts/tools/build_docs/build_docs.sh @@ -5,4 +5,4 @@ docker run --rm \ -e "WITH_AVX=ON" \ -e "WITH_DOC=ON" \ -e "WOBOQ=ON" \ - ${1:-"paddledev/paddle:dev"} + ${1:-"paddlepaddle/paddle:latest-dev"} diff --git a/python/.gitignore b/python/.gitignore index cc7d0ece4acaba2a3fa38a89110587fe8dffb992..1ba1d4c9b0301ed920f5303089e75dd3a8e4e3fa 100644 --- a/python/.gitignore +++ b/python/.gitignore @@ -2,6 +2,7 @@ build dist paddle.egg-info +paddlepaddle_gpu.egg-info .idea paddle/proto/*.py paddle/proto/*.pyc diff --git a/python/paddle/v2/fluid/evaluator.py b/python/paddle/v2/fluid/evaluator.py index 137c5736226b689340748d5098ca51659d5acff8..2d23ff0a1662026a41409c38dc76f066da896505 100644 --- a/python/paddle/v2/fluid/evaluator.py +++ b/python/paddle/v2/fluid/evaluator.py @@ -4,7 +4,7 @@ import layers from framework import Program, unique_name, Variable from layer_helper import LayerHelper -__all__ = ['Accuracy'] +__all__ = ['Accuracy', 'ChunkEvaluator'] def _clone_var_(block, var): @@ -132,3 +132,74 @@ class Accuracy(Evaluator): correct = layers.cast(correct, dtype='float32', **kwargs) out = layers.elementwise_div(x=correct, y=total, **kwargs) return np.array(executor.run(eval_program, fetch_list=[out])[0]) + + +class ChunkEvaluator(Evaluator): + """ + Accumulate counter numbers output by chunk_eval from mini-batches and + compute the precision recall and F1-score using the accumulated counter + numbers. + """ + + def __init__(self, + input, + label, + chunk_scheme, + num_chunk_types, + excluded_chunk_types=None, + **kwargs): + super(ChunkEvaluator, self).__init__("chunk_eval", **kwargs) + main_program = self.helper.main_program + if main_program.current_block().idx != 0: + raise ValueError("You can only invoke Evaluator in root block") + + self.num_infer_chunks = self.create_state( + dtype='int64', shape=[1], suffix='num_infer_chunks') + self.num_label_chunks = self.create_state( + dtype='int64', shape=[1], suffix='num_label_chunks') + self.num_correct_chunks = self.create_state( + dtype='int64', shape=[1], suffix='num_correct_chunks') + kwargs = {'main_program': main_program} + precision, recall, f1_score, num_infer_chunks, num_label_chunks, num_correct_chunks = layers.chunk_eval( + input=input, + label=label, + chunk_scheme=chunk_scheme, + num_chunk_types=num_chunk_types, + excluded_chunk_types=excluded_chunk_types, + **kwargs) + layers.sums( + input=[self.num_infer_chunks, num_infer_chunks], + out=self.num_infer_chunks, + **kwargs) + layers.sums( + input=[self.num_label_chunks, num_label_chunks], + out=self.num_label_chunks, + **kwargs) + layers.sums( + input=[self.num_correct_chunks, num_correct_chunks], + out=self.num_correct_chunks, + **kwargs) + + self.metrics.extend([precision, recall, f1_score]) + + def eval(self, executor, eval_program=None): + if eval_program is None: + eval_program = Program() + block = eval_program.current_block() + kwargs = {'main_program': eval_program} + num_infer_chunks, num_label_chunks, num_correct_chunks = executor.run( + eval_program, + fetch_list=[_clone_var_(block, state) for state in self.states]) + num_infer_chunks = num_infer_chunks[0] + num_label_chunks = num_label_chunks[0] + num_correct_chunks = num_correct_chunks[0] + precision = float( + num_correct_chunks) / num_infer_chunks if num_infer_chunks else 0 + recall = float( + num_correct_chunks) / num_label_chunks if num_label_chunks else 0 + f1_score = float(2 * precision * recall) / ( + precision + recall) if num_correct_chunks else 0 + return np.array( + [precision], dtype='float32'), np.array( + [recall], dtype='float32'), np.array( + [f1_score], dtype='float32') diff --git a/python/paddle/v2/fluid/layers.py b/python/paddle/v2/fluid/layers.py deleted file mode 100644 index 1f45487902a96856dfb411aca8d66a972abbdf38..0000000000000000000000000000000000000000 --- a/python/paddle/v2/fluid/layers.py +++ /dev/null @@ -1,2183 +0,0 @@ -import core -import proto.framework_pb2 as framework_pb2 -from framework import OpProtoHolder, Variable, Program, Operator -from initializer import Constant, Normal, Xavier, Initializer -from paddle.v2.fluid.layer_helper import LayerHelper, unique_name -import re -import cStringIO -from param_attr import ParamAttr -import contextlib - -__all__ = [ - 'fc', 'data', 'cross_entropy', 'conv2d', 'pool2d', 'embedding', 'concat', - 'StaticRNN', 'cast', 'sequence_conv', 'sequence_pool', 'sums', 'cos_sim', - 'batch_norm', 'accuracy', 'split_lod_tensor', 'While' -] - - -def fc(input, - size, - num_flatten_dims=1, - param_attr=None, - bias_attr=None, - act=None, - name=None, - main_program=None, - startup_program=None): - """ - Fully Connected Layer. - - Args: - input: The input tensor to the function - size: The size of the layer - num_flatten_dims: Number of columns in input - param_attr: The parameters/weights to the FC Layer - param_initializer: Initializer used for the weight/parameter. If None, XavierInitializer() is used - bias_attr: The bias parameter for the FC layer - bias_initializer: Initializer used for the bias. If None, then ConstantInitializer() is used - act: Activation to be applied to the output of FC layer - name: Name/alias of the function - main_program: Name of the main program that calls this - startup_program: Name of the startup program - - This function can take in multiple inputs and performs the Fully Connected - function (linear transformation) on top of each of them. - So for input x, the output will be : Wx + b. Where W is the parameter, - b the bias and x is the input. - - The function also applies an activation (non-linearity) on top of the - output, if activation is passed in the input. - - All the input variables of this function are passed in as local variables - to the LayerHelper constructor. - - """ - helper = LayerHelper('fc', **locals()) - - dtype = helper.input_dtype() - - mul_results = [] - for input_var, param_attr in helper.iter_inputs_and_params(): - input_shape = input_var.shape - param_shape = [ - reduce(lambda a, b: a * b, input_shape[num_flatten_dims:], 1) - ] + [size] - w = helper.create_parameter( - attr=param_attr, shape=param_shape, dtype=dtype, is_bias=False) - tmp = helper.create_tmp_variable(dtype) - helper.append_op( - type="mul", - inputs={ - "X": input_var, - "Y": w, - }, - outputs={"Out": tmp}, - attrs={'x_num_col_dims': num_flatten_dims, - 'y_num_col_dims': 1}) - mul_results.append(tmp) - - # sum - if len(mul_results) == 1: - pre_bias = mul_results[0] - else: - pre_bias = helper.create_tmp_variable(dtype) - helper.append_op( - type="sum", inputs={"X": mul_results}, outputs={"Out": pre_bias}) - # add bias - pre_activation = helper.append_bias_op(pre_bias) - # add activation - return helper.append_activation(pre_activation) - - -def embedding(input, - size, - is_sparse=False, - param_attr=None, - dtype='float32', - main_program=None, - startup_program=None): - """ - Embedding Layer. - - Args: - param_initializer: - input: The input to the function - size: The size of the layer - is_sparse: A flag that decleares whether the input is sparse - param_attr: Parameters for this layer - dtype: The type of data : float32, float_16, int etc - main_program: Name of the main program that calls this - startup_program: Name of the startup program - - This function can take in the input (which is a vector of IDs) and - performs a lookup in the lookup_table using these IDs, to result into - the embedding of each ID in the input. - - All the input variables of this function are passed in as local variables - to the LayerHelper constructor. - - """ - - helper = LayerHelper('embedding', **locals()) - w = helper.create_parameter( - attr=helper.param_attr, shape=size, dtype=dtype, is_bias=False) - tmp = helper.create_tmp_variable(dtype) - helper.append_op( - type='lookup_table', - inputs={'Ids': input, - 'W': w}, - outputs={'Out': tmp}, - attrs={'is_sparse': is_sparse}) - return tmp - - -# TODO(qijun): expose H0 and C0 -def dynamic_lstm(input, - size, - param_attr=None, - bias_attr=None, - use_peepholes=True, - is_reverse=False, - gate_activation='sigmoid', - cell_activation='tanh', - candidate_activation='tanh', - dtype='float32', - main_program=None, - startup_program=None): - helper = LayerHelper('lstm', **locals()) - size = size / 4 - weight = helper.create_parameter( - attr=helper.param_attr, shape=[size, 4 * size], dtype=dtype) - bias_size = [1, 7 * size] - if not use_peepholes: - bias_size[1] = 4 * size - bias = helper.create_parameter( - attr=helper.bias_attr, shape=bias_size, dtype=dtype, is_bias=True) - - hidden = helper.create_tmp_variable(dtype) - cell = helper.create_tmp_variable(dtype) - batch_gate = helper.create_tmp_variable(dtype) - batch_cell_pre_act = helper.create_tmp_variable(dtype) - - helper.append_op( - type='lstm', - inputs={'Input': input, - 'Weight': weight, - 'Bias': bias}, - outputs={ - 'Hidden': hidden, - 'Cell': cell, - 'BatchGate': batch_gate, - 'BatchCellPreAct': batch_cell_pre_act - }, - attrs={ - 'use_peepholes': use_peepholes, - 'is_reverse': is_reverse, - 'gate_activation': gate_activation, - 'cell_activation': cell_activation, - 'candidate_activation': candidate_activation - }) - return hidden, cell - - -def gru_unit(input, - hidden, - size, - weight=None, - bias=None, - activation='tanh', - gate_activation='sigmoid', - main_program=None, - startup_program=None): - """ - GRUUnit Operator implements partial calculations of the GRU unit as following: - - $$ - update \ gate: u_t = actGate(xu_t + W_u * h_{t-1} + b_u) \\ - reset \ gate: r_t = actGate(xr_t + W_r * h_{t-1} + b_r) \\ - output \ candidate: {h}_t = actNode(xc_t + W_c * dot(r_t, h_{t-1}) + b_c) \\ - output: h_t = dot((1 - u_t), h_{t-1}) + dot(u_t, {h}_t) - $$ - - which is same as one time step of GRU Operator. - - @note To implement the complete GRU unit, fully-connected operator must be - used before to feed xu, xr and xc as the Input of GRUUnit operator. - - TODO(ChunweiYan) add more document here - """ - activation_dict = dict( - identity=0, - sigmoid=1, - tanh=2, - relu=3, ) - activation = activation_dict[activation] - gate_activation = activation_dict[gate_activation] - - helper = LayerHelper('gru_unit', **locals()) - dtype = helper.input_dtype() - size = size / 3 - - # create weight - if weight is None: - weight = helper.create_parameter( - attr=helper.param_attr, shape=[size, 3 * size], dtype=dtype) - - # create bias - if bias is None: - bias_size = [1, 3 * size] - bias = helper.create_parameter( - attr=helper.bias_attr, shape=bias_size, dtype=dtype, is_bias=True) - - gate = helper.create_tmp_variable(dtype) - reset_hidden_pre = helper.create_tmp_variable(dtype) - updated_hidden = helper.create_tmp_variable(dtype) - - helper.append_op( - type='gru_unit', - inputs={'Input': input, - 'HiddenPrev': hidden, - 'Weight': weight}, - outputs={ - 'Gate': gate, - 'ResetHiddenPrev': reset_hidden_pre, - 'Hidden': updated_hidden, - }, - attrs={ - 'activation': 0, - 'gate_activation': 1, - }) - - return updated_hidden, reset_hidden_pre, gate - - -def data(name, - shape, - append_batch_size=True, - dtype='float32', - lod_level=0, - type=core.VarDesc.VarType.LOD_TENSOR, - main_program=None, - startup_program=None, - stop_gradient=True): - """ - Data Layer. - - Args: - name: The name/alias of the function - shape: Tuple declaring the shape. - append_batch_size: Whether or not to append the data as a batch. - dtype: The type of data : float32, float_16, int etc - type: The output type. By default it is LOD_TENSOR. - lod_level(int): The LoD Level. 0 means the input data is not a sequence. - main_program: Name of the main program that calls this - startup_program: Name of the startup program - stop_gradient: A boolean that mentions whether gradient should flow. - - This function takes in input and based on whether data has - to be returned back as a minibatch, it creates the global variable using - the helper functions. The global variables can be accessed by all the - following operations and layers in the graph. - - All the input variables of this function are passed in as local variables - to the LayerHelper constructor. - - """ - helper = LayerHelper('data', **locals()) - shape = list(shape) - for i in xrange(len(shape)): - if shape[i] is None: - shape[i] = -1 - append_batch_size = False - elif shape[i] < 0: - append_batch_size = False - - if append_batch_size: - shape = [-1] + shape # append batch size as -1 - - return helper.create_global_variable( - name=name, - shape=shape, - dtype=dtype, - type=type, - stop_gradient=stop_gradient, - lod_level=lod_level) - - -def create_tensor(dtype, name=None, main_program=None, startup_program=None): - helper = LayerHelper("create_tensor", **locals()) - return helper.create_variable(name=helper.name, dtype=dtype) - - -def _convert_(name): - """ - Formatting. - - Args: - name: The name/alias - - This function takes in a name and converts it to a standard format of - group1_group2. Where as per the regular expression, group1 can have - alphabets and numbers and group2 has capital alphabets. - - """ - s1 = re.sub('(.)([A-Z][a-z]+)', r'\1_\2', name) - return re.sub('([a-z0-9])([A-Z])', r'\1_\2', s1).lower() - - -def _generate_doc_string_(op_proto): - """ - Generate docstring by OpProto - - Args: - op_proto (framework_pb2.OpProto): a protobuf message typed OpProto - - Returns: - str: the document string - """ - - def _type_to_str_(tp): - return framework_pb2.AttrType.Name(tp) - - if not isinstance(op_proto, framework_pb2.OpProto): - raise TypeError("OpProto should be `framework_pb2.OpProto`") - - buf = cStringIO.StringIO() - buf.write(op_proto.comment) - buf.write('\nArgs:\n') - for each_input in op_proto.inputs: - line_begin = ' {0}: '.format(_convert_(each_input.name)) - buf.write(line_begin) - buf.write(each_input.comment) - buf.write('\n') - buf.write(' ' * len(line_begin)) - buf.write('Duplicable: ') - buf.write(str(each_input.duplicable)) - buf.write(' Optional: ') - buf.write(str(each_input.dispensable)) - buf.write('\n') - - for each_attr in op_proto.attrs: - buf.write(' ') - buf.write(each_attr.name) - buf.write(' (') - buf.write(_type_to_str_(each_attr.type)) - buf.write('): ') - buf.write(each_attr.comment) - buf.write('\n') - - if len(op_proto.outputs) != 0: - buf.write('\nReturns:\n') - buf.write(' ') - for each_opt in op_proto.outputs: - if not each_opt.intermediate: - break - buf.write(each_opt.comment) - - return buf.getvalue() - - -def _create_op_func_(op_type): - """ - Create an Operator for a Function. - - Args: - op_type: The name of the operator to be created - - This function takes in the operator type (sigmoid, mean , average etc) and - creates the operator functionality. - - """ - op_proto = OpProtoHolder.instance().get_op_proto(op_type) - not_intermediate_outputs = \ - filter(lambda output: not output.intermediate, op_proto.outputs) - intermediate_outputs = \ - filter(lambda output: output.intermediate, op_proto.outputs) - - if len(not_intermediate_outputs) != 1: - raise ValueError("Only one non intermediate output operator can be", - "automatically generated") - - if not_intermediate_outputs[0].duplicable: - raise ValueError( - "Only non duplicable op can be automatically generated") - - for output in intermediate_outputs: - if output.duplicable: - raise ValueError("The op can be automatically generated only when ", - "all intermediate ops are not duplicable") - - o_name = not_intermediate_outputs[0].name - intermediate_output_names = [output.name for output in intermediate_outputs] - - def infer_and_check_dtype(op_proto, **kwargs): - """ - This function performs the sanity check for dtype and - instance type. - """ - dtype = None - for ipt in op_proto.inputs: - name = _convert_(ipt.name) - val = kwargs.pop(name, []) - if not isinstance(val, list) and not isinstance(val, tuple): - val = [val] - for each in val: - if not isinstance(each, Variable): - raise ValueError("input of {0} must be variable".format( - op_type)) - - if dtype is None: - dtype = each.dtype - elif dtype != each.dtype: - raise ValueError( - "operator {0} must input same dtype. {1} vs {2}".format( - op_type, dtype, each.dtype)) - - return dtype - - def func(**kwargs): - helper = LayerHelper(op_type, **kwargs) - - dtype = infer_and_check_dtype(op_proto, **kwargs) - - inputs = dict() - for ipt in op_proto.inputs: - name = _convert_(ipt.name) - val = kwargs.pop(name, []) - if not isinstance(val, list) and not isinstance(val, tuple): - val = [val] - inputs[ipt.name] = val - - outputs = dict() - out = helper.create_tmp_variable(dtype=dtype) - outputs[o_name] = [out] - for name in intermediate_output_names: - outputs[name] = [helper.create_tmp_variable(dtype=dtype)] - helper.append_op( - type=op_type, inputs=inputs, outputs=outputs, attrs=kwargs) - return helper.append_activation(out) - - func.__name__ = op_type - globals()[op_type] = func - func.__doc__ = _generate_doc_string_(op_proto) - global __all__ - __all__.append(op_type) - - -_create_op_func_('mean') -_create_op_func_('mul') -_create_op_func_('elementwise_add') -_create_op_func_('elementwise_div') -_create_op_func_('dropout') -_create_op_func_('reshape') -_create_op_func_('sigmoid') -_create_op_func_('scale') -_create_op_func_('reshape') -_create_op_func_('transpose') -_create_op_func_('sigmoid_cross_entropy_with_logits') - - -def cast(x, dtype, main_program=None): - """ - This function takes in the input with input_dtype - and casts it to the output_dtype as the output. - """ - helper = LayerHelper('cast', **locals()) - out = helper.create_tmp_variable(dtype=dtype) - helper.append_op( - type='cast', - inputs={'X': [x]}, - outputs={'Out': [out]}, - attrs={'in_dtype': x.dtype, - 'out_dtype': out.dtype}) - return out - - -def concat(input, axis, main_program=None, startup_program=None): - """ - This function concats the input along the axis mentioned - and returns that as the output. - """ - helper = LayerHelper('concat', **locals()) - out = helper.create_tmp_variable(dtype=helper.input_dtype()) - helper.append_op( - type='concat', - inputs={'X': input}, - outputs={'Out': [out]}, - attrs={'axis': axis}) - return out - - -def sums(input, out=None, main_program=None, startup_program=None): - """ - This function takes in the input and performs the sum operation on it - and returns that as the output. - """ - helper = LayerHelper('sum', **locals()) - if out is None: - out = helper.create_tmp_variable(dtype=helper.input_dtype()) - helper.append_op(type='sum', inputs={'X': input}, outputs={'Out': out}) - return out - - -def linear_chain_crf(input, - label, - param_attr=None, - main_program=None, - startup_program=None): - helper = LayerHelper('linear_chain_crf', **locals()) - size = input.shape[1] - transition = helper.create_parameter( - attr=helper.param_attr, - shape=[size + 2, size], - dtype=helper.input_dtype()) - alpha = helper.create_tmp_variable(dtype=helper.input_dtype()) - emission_exps = helper.create_tmp_variable(dtype=helper.input_dtype()) - transition_exps = helper.create_tmp_variable(dtype=helper.input_dtype()) - log_likelihood = helper.create_tmp_variable(dtype=helper.input_dtype()) - helper.append_op( - type='linear_chain_crf', - inputs={"Emission": [input], - "Transition": transition, - "Label": label}, - outputs={ - "Alpha": [alpha], - "EmissionExps": [emission_exps], - "TransitionExps": transition_exps, - "LogLikelihood": log_likelihood - }) - - return log_likelihood - - -def crf_decoding(input, - param_attr, - label=None, - main_program=None, - startup_program=None): - helper = LayerHelper('crf_decoding', **locals()) - transition = helper.get_parameter(param_attr.name) - viterbi_path = helper.create_tmp_variable(dtype=helper.input_dtype()) - helper.append_op( - type='crf_decoding', - inputs={"Emission": [input], - "Transition": transition, - "Label": label}, - outputs={"ViterbiPath": [viterbi_path]}) - - return viterbi_path - - -def assign(input, output, main_program=None, startup_program=None): - helper = LayerHelper('assign', **locals()) - helper.append_op( - type='scale', - inputs={'X': [input]}, - outputs={'Out': [output]}, - attrs={'scale': 1.0}) - return output - - -def split_lod_tensor(input, - mask, - level=0, - main_program=None, - startup_program=None): - helper = LayerHelper('split_lod_tensor', **locals()) - out_true = helper.create_tmp_variable(dtype=input.dtype) - out_false = helper.create_tmp_variable(dtype=input.dtype) - helper.append_op( - type='split_lod_tensor', - inputs={ - 'X': input, - 'Mask': mask, - }, - outputs={'OutTrue': out_true, - 'OutFalse': out_false}, - attrs={'level': level}) - return out_true, out_false - - -def merge_lod_tensor(in_true, - in_false, - x, - mask, - level=0, - main_program=None, - startup_program=None): - helper = LayerHelper('merge_lod_tensor', **locals()) - out = helper.create_tmp_variable(dtype=in_true.dtype) - helper.append_op( - type='merge_lod_tensor', - inputs={'X': x, - 'Mask': mask, - 'InTrue': in_true, - 'InFalse': in_false}, - outputs={'Out': out}, - attrs={'level': level}) - return out - - -def cos_sim(X, Y, **kwargs): - """ - This function performs the cosine similarity between two tensors - X and Y and returns that as the output. - """ - helper = LayerHelper('cos_sim', **kwargs) - out = helper.create_tmp_variable(dtype=X.dtype) - xnorm = helper.create_tmp_variable(dtype=X.dtype) - ynorm = helper.create_tmp_variable(dtype=X.dtype) - helper.append_op( - type='cos_sim', - inputs={'X': [X], - 'Y': [Y]}, - outputs={'Out': [out], - 'XNorm': [xnorm], - 'YNorm': [ynorm]}) - return out - - -def cross_entropy(input, label, **kwargs): - """ - This function computes cross_entropy using the input and label. - """ - helper = LayerHelper('cross_entropy', **kwargs) - out = helper.create_tmp_variable(dtype=input.dtype) - helper.append_op( - type='cross_entropy', - inputs={'X': [input], - 'Label': [label]}, - outputs={'Y': [out]}, - attrs=kwargs) - return out - - -def square_error_cost(input, label, **kwargs): - """ - This functions returns the squared error cost using the input and label. - The output is appending the op to do the above. - """ - helper = LayerHelper('square_error_cost', **kwargs) - minus_out = helper.create_tmp_variable(dtype=input.dtype) - helper.append_op( - type='elementwise_sub', - inputs={'X': [input], - 'Y': [label]}, - outputs={'Out': [minus_out]}) - - square_out = helper.create_tmp_variable(dtype=input.dtype) - helper.append_op( - type='square', inputs={'X': [minus_out]}, outputs={'Y': [square_out]}) - return square_out - - -def accuracy(input, label, k=1, correct=None, total=None, **kwargs): - """ - This function computes the accuracy using the input and label. - The output is the top_k inputs and their indices. - """ - helper = LayerHelper("accuracy", **kwargs) - topk_out = helper.create_tmp_variable(dtype=input.dtype) - topk_indices = helper.create_tmp_variable(dtype="int64") - helper.append_op( - type="top_k", - inputs={"X": [input]}, - outputs={"Out": [topk_out], - "Indices": [topk_indices]}, - attrs={"k": k}) - acc_out = helper.create_tmp_variable(dtype="float32") - if correct is None: - correct = helper.create_tmp_variable(dtype="int64") - if total is None: - total = helper.create_tmp_variable(dtype="int64") - helper.append_op( - type="accuracy", - inputs={ - "Out": [topk_out], - "Indices": [topk_indices], - "Label": [label] - }, - outputs={ - "Accuracy": [acc_out], - "Correct": [correct], - "Total": [total], - }) - return acc_out - - -def chunk_eval(input, - label, - chunk_scheme, - num_chunk_types, - excluded_chunk_types=None, - **kwargs): - """ - This function computes the accuracy using the input and label. - The output is the top_k inputs and their indices. - """ - helper = LayerHelper("chunk_eval", **kwargs) - - # prepare output - precision = helper.create_tmp_variable(dtype="float32") - recall = helper.create_tmp_variable(dtype="float32") - f1_score = helper.create_tmp_variable(dtype="float32") - - helper.append_op( - type="chunk_eval", - inputs={"Inference": [input], - "Label": [label]}, - outputs={ - "Precision": [precision], - "Recall": [recall], - "F1-Score": [f1_score] - }, - attrs={ - "num_chunk_types": num_chunk_types, - 'chunk_scheme': chunk_scheme, - 'excluded_chunk_types': excluded_chunk_types or [] - }) - return precision, recall, f1_score - - -def sequence_conv(input, - num_filters, - filter_size=3, - filter_stride=1, - padding=None, - bias_attr=None, - param_attr=None, - act=None, - main_program=None, - startup_program=None): - """ - This function creates the op for sequence_conv, using the inputs and - other convolutional configurations for the filters and stride as given - in the input parameters to the function. - """ - - # FIXME(dzh) : want to unify the argument of python layer - # function. So we ignore some unecessary attributes. - # such as, padding_trainable, context_start. - - helper = LayerHelper('sequence_conv', **locals()) - dtype = helper.input_dtype() - filter_shape = [filter_size * input.shape[1], num_filters] - filter_param = helper.create_parameter( - attr=helper.param_attr, shape=filter_shape, dtype=dtype) - pre_bias = helper.create_tmp_variable(dtype) - - helper.append_op( - type='sequence_conv', - inputs={ - 'X': [input], - 'Filter': [filter_param], - }, - outputs={"Out": pre_bias}, - attrs={ - 'contextStride': filter_stride, - 'contextStart': -int(filter_size / 2), - 'contextLength': filter_size - }) - pre_act = helper.append_bias_op(pre_bias) - return helper.append_activation(pre_act) - - -def conv2d(input, - num_filters, - filter_size, - stride=None, - padding=None, - groups=None, - param_attr=None, - bias_attr=None, - act=None, - name=None, - main_program=None, - startup_program=None): - """ - This function creates the op for a 2-dimensional Convolution. - This is performed using the parameters of filters(size, dimensionality etc) - , stride and other configurations for a Convolution operation. - This funciton can also append an activation on top of the - conv-2d output, if mentioned in the input parameters. - """ - - if stride is None: - stride = [1, 1] - helper = LayerHelper('conv2d', **locals()) - dtype = helper.input_dtype() - - num_channels = input.shape[1] - if groups is None: - num_filter_channels = num_channels - else: - if num_channels % groups != 0: - raise ValueError("num_channels must be divisible by groups.") - num_filter_channels = num_channels / groups - - if isinstance(filter_size, int): - filter_size = [filter_size, filter_size] - if isinstance(stride, int): - stride = [stride, stride] - if isinstance(padding, int): - padding = [padding, padding] - - input_shape = input.shape - filter_shape = [num_filters, num_filter_channels] + filter_size - - def _get_default_param_initializer(): - std = (2.0 / (filter_size[0]**2 * num_channels))**0.5 - return Normal(0.0, std, 0) - - filter_param = helper.create_parameter( - attr=helper.param_attr, - shape=filter_shape, - dtype=dtype, - default_initializer=_get_default_param_initializer()) - - pre_bias = helper.create_tmp_variable(dtype) - - helper.append_op( - type='conv2d_cudnn', - inputs={ - 'Input': input, - 'Filter': filter_param, - }, - outputs={"Output": pre_bias}, - attrs={'strides': stride, - 'paddings': padding, - 'groups': groups}) - - pre_act = helper.append_bias_op(pre_bias, dim_start=1, dim_end=2) - - return helper.append_activation(pre_act) - - -def sequence_pool(input, pool_type, **kwargs): - """ - This function add the operator for sequence pooling. - This is applied on top of the input using pool_type mentioned - in the parameters. - """ - helper = LayerHelper('sequence_pool', input=input, **kwargs) - dtype = helper.input_dtype() - pool_out = helper.create_tmp_variable(dtype) - max_index = helper.create_tmp_variable(dtype) - - helper.append_op( - type="sequence_pool", - inputs={"X": input}, - outputs={"Out": pool_out, - "MaxIndex": max_index}, - attrs={"pooltype": pool_type.upper()}) - - return pool_out - - -def pool2d(input, - pool_size, - pool_type, - pool_stride=None, - pool_padding=None, - global_pooling=False, - main_program=None, - startup_program=None): - """ - This function adds the operator for pooling in 2 dimensions, using the - pooling configurations mentioned in input parameters. - """ - if pool_padding is None: - pool_padding = [0, 0] - if pool_stride is None: - pool_stride = [1, 1] - if pool_type not in ["max", "avg"]: - raise ValueError( - "Unknown pool_type: '%s'. It can only be 'max' or 'avg'.", - str(pool_type)) - if isinstance(pool_size, int): - pool_size = [pool_size, pool_size] - if isinstance(pool_stride, int): - pool_stride = [pool_stride, pool_stride] - if isinstance(pool_padding, int): - pool_padding = [pool_padding, pool_padding] - - helper = LayerHelper('pool2d', **locals()) - dtype = helper.input_dtype() - pool_out = helper.create_tmp_variable(dtype) - - helper.append_op( - type="pool2d", - inputs={"X": input}, - outputs={"Out": pool_out}, - attrs={ - "pooling_type": pool_type, - "ksize": pool_size, - "global_pooling": global_pooling, - "strides": pool_stride, - "paddings": pool_padding - }) - - return pool_out - - -def batch_norm(input, - act=None, - is_test=False, - momentum=0.9, - epsilon=1e-05, - param_attr=None, - bias_attr=None, - data_layout='NCHW', - main_program=None, - startup_program=None): - """ - This function helps create an operator to implement - the BatchNorm layer using the configurations from the input parameters. - """ - helper = LayerHelper('batch_norm', **locals()) - dtype = helper.input_dtype() - - input_shape = input.shape - if data_layout == 'NCHW': - channel_num = input_shape[1] - else: - if data_layout == 'NHWC': - channel_num = input_shape[-1] - else: - raise ValueError("unsupported data layout:" + data_layout) - - param_shape = [channel_num] - - # create parameter - scale = helper.create_parameter( - attr=helper.param_attr, - shape=param_shape, - dtype=dtype, - default_initializer=Constant(1.0)) - - bias = helper.create_parameter( - attr=helper.param_attr, shape=param_shape, dtype=dtype, is_bias=True) - - mean = helper.create_global_variable( - dtype=input.dtype, shape=param_shape, persistable=True) - helper.set_variable_initializer(var=mean, initializer=Constant(0.0)) - - variance = helper.create_global_variable( - dtype=input.dtype, shape=param_shape, persistable=True) - helper.set_variable_initializer(var=variance, initializer=Constant(1.0)) - - # create output - # mean and mean_out share the same memory - mean_out = mean - # variance and variance out share the same memory - variance_out = variance - saved_mean = helper.create_tmp_variable(dtype) - saved_variance = helper.create_tmp_variable(dtype) - - batch_norm_out = helper.create_tmp_variable(dtype) - - helper.append_op( - type="batch_norm", - inputs={ - "X": input, - "Scale": scale, - "Bias": bias, - "Mean": mean, - "Variance": variance - }, - outputs={ - "Y": batch_norm_out, - "MeanOut": mean_out, - "VarianceOut": variance_out, - "SavedMean": saved_mean, - "SavedVariance": saved_variance - }, - attrs={"momentum": momentum, - "epsilon": epsilon, - "is_test": is_test}) - - return helper.append_activation(batch_norm_out) - - -def beam_search_decode(ids, scores, main_program=None, startup_program=None): - helper = LayerHelper('beam_search_decode', **locals()) - sentence_ids = helper.create_tmp_variable(dtype=ids.dtype) - sentence_scores = helper.create_tmp_variable(dtype=ids.dtype) - - helper.append_op( - type="beam_search_decode", - inputs={"Ids": ids, - "Scores": scores}, - outputs={ - "SentenceIds": sentence_ids, - "SentenceScores": sentence_scores - }) - - return sentence_ids, sentence_scores - - -class BlockGuard(object): - """ - BlockGuard class. - - BlockGuard class is used to create a sub-block in a program by - using the Python `with` keyword. - """ - - def __init__(self, main_program): - if not isinstance(main_program, Program): - raise TypeError("BlockGuard takes a program") - self.main_program = main_program - - def __enter__(self): - self.main_program.create_block() - - def __exit__(self, exc_type, exc_val, exc_tb): - self.main_program.rollback() - if exc_type is not None: - return False # re-raise exception - return True - - -class StaticRNNGuard(BlockGuard): - """ - StaticRNNGuard class. - - StaticRNNGuard class is used to create a StaticRNN block in a program. - """ - - def __init__(self, rnn): - if not isinstance(rnn, StaticRNN): - raise TypeError("StaticRNNGuard takes a StaticRNN") - super(StaticRNNGuard, self).__init__(rnn.helper.main_program) - self.rnn = rnn - - def __enter__(self): - self.rnn.status = StaticRNN.IN_RNN_BLOCK - return super(StaticRNNGuard, self).__enter__() - - def __exit__(self, exc_type, exc_val, exc_tb): - if exc_type is not None: - return False - self.rnn.status = StaticRNN.AFTER_RNN_BLOCK - self.rnn.complete_rnn_op() - return super(StaticRNNGuard, self).__exit__(exc_type, exc_val, exc_tb) - - -class StaticRNNMemoryLink(object): - """ - StaticRNNMemoryLink class. - - Args: - init: the initial variable for Memory - init: Variable - pre_mem: the memory variable in previous time step - pre_mem: Variable - mem: the memory variable in current time step - mem: Variable - - StaticRNNMemoryLink class is used to create a link between two - memory cells of a StaticRNN. - """ - - def __init__(self, init, pre_mem, mem=None): - self.init = init - self.pre_mem = pre_mem - self.mem = mem - - -class StaticRNN(object): - """ - StaticRNN class. - - StaticRNN class is used to create a StaticRNN. The RNN will have its - own parameters like inputs, outputs, memories, status and length. - """ - BEFORE_RNN_BLOCK = 0 - IN_RNN_BLOCK = 1 - AFTER_RNN_BLOCK = 2 - - def __init__(self, name=None, main_program=None): - self.helper = LayerHelper( - "static_rnn", name=name, main_program=main_program) - self.memories = {} # memory map, from pre_mem.name --> MemoryLink - self.inputs = [] # input variable list in current block - self.outputs = [] # output variable list in parent block - self.status = StaticRNN.BEFORE_RNN_BLOCK # status flag. - # sequence length, since it is a static RNN, sequence length are fixed. - self.seq_len = None - - def step(self): - return StaticRNNGuard(self) - - def _assert_in_rnn_block_(self, method): - if self.status != StaticRNN.IN_RNN_BLOCK: - raise ValueError("You must invoke {0} in rnn block".format(method)) - - def memory(self, - init=None, - shape=None, - batch_ref=None, - init_value=0.0, - init_batch_dim_idx=0, - ref_batch_dim_idx=1): - """ - Args: - init: boot memory, if not set, a shape, batch_ref must be provided - shape: shape of the boot memory - batch_ref: batch size reference variable - init_value: the init value of boot memory - init_batch_dim_idx: the index of batch size in init's dimension - ref_batch_dim_idx: the index of batch size in batch_ref's dimension - """ - self._assert_in_rnn_block_('memory') - if init is None: - if shape is None or batch_ref is None: - raise ValueError( - "if init is None, memory at least need shape and batch_ref") - parent_block = self.parent_block() - var_name = unique_name("@".join([self.helper.name, "memory_boot"])) - boot_var = parent_block.create_var( - name=var_name, - shape=shape, - dtype=batch_ref.dtype, - persistable=False) - - parent_block.append_op( - type="fill_constant_batch_size_like", - inputs={'Input': [batch_ref]}, - outputs={'Out': [boot_var]}, - attrs={ - 'value': init_value, - 'shape': boot_var.shape, - 'dtype': boot_var.dtype, - 'input_dim_idx': ref_batch_dim_idx, - 'output_dim_idx': init_batch_dim_idx - }) - - return self.memory(init=boot_var) - else: - pre_mem = self.helper.create_variable( - name=unique_name("@".join([self.helper.name, "mem"])), - dtype=init.dtype, - shape=init.shape) - self.memories[pre_mem.name] = StaticRNNMemoryLink( - init=init, pre_mem=pre_mem) - return pre_mem - - def step_input(self, x): - self._assert_in_rnn_block_('step_input') - if not isinstance(x, Variable): - raise TypeError("step input takes a Variable") - if self.seq_len is None: - self.seq_len = x.shape[0] - elif self.seq_len != x.shape[0]: - raise ValueError("Static RNN only take fix seq_len input") - - ipt = self.helper.create_variable( - name=x.name, dtype=x.dtype, shape=list(x.shape[1:]), type=x.type) - self.inputs.append(ipt) - return ipt - - def step_output(self, o): - self._assert_in_rnn_block_('step_output') - if not isinstance(o, Variable): - raise TypeError("step output takes a Variable") - - tmp_o = self.helper.create_tmp_variable(dtype=o.dtype) - self.helper.append_op( - type='rnn_memory_helper', - inputs={'X': [o]}, - outputs={'Out': tmp_o}, - attrs={'dtype': o.dtype}) - - out_var = self.parent_block().create_var( - name=tmp_o.name, - shape=[self.seq_len] + list(tmp_o.shape), - dtype=tmp_o.dtype) - - self.outputs.append(out_var) - - def output(self, *outputs): - for each in outputs: - self.step_output(each) - - def update_memory(self, mem, var): - if not isinstance(mem, Variable) or not isinstance(var, Variable): - raise TypeError("update memory should take variables") - self.memories[mem.name].mem = var - - def parent_block(self): - prog = self.helper.main_program - parent_idx = prog.current_block().parent_idx - assert parent_idx >= 0 - parent_block = prog.block(parent_idx) - return parent_block - - def __call__(self, *args, **kwargs): - if self.status != StaticRNN.AFTER_RNN_BLOCK: - raise ValueError("RNN output can only be retrieved after rnn block") - if len(self.outputs) == 0: - raise ValueError("RNN has no output") - elif len(self.outputs) == 1: - return self.outputs[0] - else: - return self.outputs - - def complete_rnn_op(self): - main_program = self.helper.main_program - rnn_block = main_program.current_block() - parent_block = self.parent_block() - - local_inputs = set() - - for op in rnn_block.ops: - assert isinstance(op, Operator) - for oname in op.output_names: - for out_var_name in op.output(oname): - local_inputs.add(out_var_name) - - for var in self.inputs: - local_inputs.add(var.name) - for m in self.memories: - local_inputs.add(m) - - params = list() - for op in rnn_block.ops: - assert isinstance(op, Operator) - for iname in op.input_names: - for in_var_name in op.input(iname): - if in_var_name not in local_inputs: - params.append(in_var_name) - - parameters = [parent_block.var(name) for name in params] - - step_scope = parent_block.create_var( - type=core.VarDesc.VarType.STEP_SCOPES) - - inlinks = [parent_block.var(i.name) for i in self.inputs] - outlinks = self.outputs - - boot_memories = [] - pre_memories = [] - memories = [] - for _, mem in self.memories.iteritems(): - boot_memories.append(mem.init) - pre_memories.append(mem.pre_mem.name) - mem_var = rnn_block.var(mem.mem.name) - assert isinstance(mem_var, Variable) - new_mem = self.helper.create_tmp_variable(dtype=mem_var.dtype) - - rnn_block.append_op( - type='rnn_memory_helper', - inputs={'X': [mem_var]}, - outputs={'Out': [new_mem]}, - attrs={'dtype': mem_var.dtype}) - - memories.append(new_mem.name) - - parent_block.append_op( - type='recurrent', - inputs={ - 'inputs': inlinks, - 'initial_states': boot_memories, - 'parameters': parameters - }, - outputs={'outputs': outlinks, - 'step_scopes': [step_scope]}, - attrs={ - 'ex_states': pre_memories, - 'states': memories, - 'step_block': rnn_block - }) - - -class WhileGuard(BlockGuard): - def __init__(self, while_op): - if not isinstance(while_op, While): - raise TypeError("WhileGuard takes a while op") - super(WhileGuard, self).__init__(while_op.helper.main_program) - self.while_op = while_op - - def __enter__(self): - self.while_op.status = While.IN_WHILE_BLOCK - return super(WhileGuard, self).__enter__() - - def __exit__(self, exc_type, exc_val, exc_tb): - if exc_type is not None: - return False - self.while_op.status = While.AFTER_WHILE_BLOCK - self.while_op.complete() - return super(WhileGuard, self).__exit__(exc_type, exc_val, exc_tb) - - -class While(object): - BEFORE_WHILE_BLOCK = 0 - IN_WHILE_BLOCK = 1 - AFTER_WHILE_BLOCK = 2 - - def __init__(self, cond, name=None, main_program=None): - self.helper = LayerHelper("while", name=name, main_program=main_program) - self.status = While.BEFORE_WHILE_BLOCK - if not isinstance(cond, Variable): - raise TypeError("condition should be a variable") - assert isinstance(cond, Variable) - if cond.dtype != core.DataType.BOOL: - raise TypeError("condition should be a bool variable") - if reduce(lambda a, b: a * b, cond.shape, 1) != 1: - raise TypeError("condition should be a bool scalar") - self.cond_var = cond - - def block(self): - return WhileGuard(self) - - def complete(self): - main_program = self.helper.main_program - while_block = main_program.current_block() - parent_block = main_program.block(main_program.current_block() - .parent_idx) - - inner_outputs = {self.cond_var.name} - x_name_list = set() - for op in while_block.ops: - for iname in op.input_names: - for in_var_name in op.input(iname): - if in_var_name not in inner_outputs: - x_name_list.add(in_var_name) - - for oname in op.output_names: - for out_var_name in op.output(oname): - inner_outputs.add(out_var_name) - - out_vars = [] - for inner_out_name in inner_outputs: - if inner_out_name in parent_block.vars: - out_vars.append(parent_block.var(inner_out_name)) - - step_scope = parent_block.create_var( - type=core.VarDesc.VarType.STEP_SCOPES) - - parent_block.append_op( - type='while', - inputs={ - 'X': [parent_block.var(x_name) for x_name in x_name_list], - 'Condition': [self.cond_var] - }, - outputs={'Out': out_vars, - 'StepScopes': [step_scope]}, - attrs={'step_block': while_block}) - - -def lstm(x, - c_pre_init, - hidden_dim, - forget_bias=None, - main_program=None, - startup_program=None): - """ - This function helps create an operator for the LSTM (Long Short Term - Memory) cell that can be used inside an RNN. - """ - helper = LayerHelper('lstm_unit', **locals()) - rnn = StaticRNN() - with rnn.step(): - c_pre = rnn.memory(init=c_pre_init) - x_t = rnn.step_input(x) - - before_fc = concat( - input=[x_t, c_pre], - axis=1, - main_program=main_program, - startup_program=startup_program) - after_fc = fc(input=before_fc, - size=hidden_dim * 4, - main_program=main_program, - startup_program=startup_program) - - dtype = x.dtype - c = helper.create_tmp_variable(dtype) - h = helper.create_tmp_variable(dtype) - - helper.append_op( - type='lstm_unit', - inputs={"X": after_fc, - "C_prev": c_pre}, - outputs={"C": c, - "H": h}, - attrs={"forget_bias": forget_bias}) - - rnn.update_memory(c_pre, c) - rnn.output(h) - - return rnn() - - -def lod_rank_table(x, level=0, main_program=None): - """ - This function creates an operator for creating a LOD_RANK_TABLE - using the input x. - """ - helper = LayerHelper("lod_rank_table", **locals()) - table = helper.create_variable( - type=core.VarDesc.VarType.LOD_RANK_TABLE, - name=unique_name("lod_rank_table")) - helper.append_op( - type='lod_rank_table', - inputs={'X': x}, - outputs={'Out': table}, - attrs={'level': level}) - return table - - -def max_sequence_len(rank_table, main_program=None): - """ - This function creates an operator to calculate the length of - max seqence through input rank_table(should be a lod_rank_table) - """ - helper = LayerHelper("max_seqence_len", **locals()) - res = helper.create_tmp_variable(dtype="int64") - helper.append_op( - type="max_sequence_len", - inputs={"RankTable": rank_table}, - outputs={"Out": res}) - return res - - -def topk(input, k, main_program=None, startup_program=None): - helper = LayerHelper('topk', **locals()) - topk_out = helper.create_tmp_variable(dtype=input.data_type) - topk_indices = helper.create_tmp_variable(dtype='int64') - helper.append_op( - type='top_k', - inputs={'X': [input]}, - outputs={'Out': [topk_out], - 'Indices': [topk_indices]}, - attrs={'k': k}) - return topk_out, topk_indices - - -def lod_tensor_to_array(x, table, main_program=None): - """ - This function creates an operator to convert an LOD_Tensor to - an array. - """ - helper = LayerHelper("lod_tensor_to_array", **locals()) - array = helper.create_variable( - name=unique_name("lod_tensor_to_array"), - type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, - dtype=x.dtype) - helper.append_op( - type='lod_tensor_to_array', - inputs={'X': x, - 'RankTable': table}, - outputs={'Out': array}) - return array - - -def array_to_lod_tensor(x, table, main_program=None, startup_program=None): - """ - This function creates an operator to convert an array to a - LOD_Tensor. - """ - helper = LayerHelper("array_to_lod_tensor", **locals()) - tmp = helper.create_tmp_variable(dtype=x.dtype) - helper.append_op( - type="array_to_lod_tensor", - inputs={'X': x, - 'RankTable': table}, - outputs={'Out': tmp}) - return tmp - - -def fill_constant(shape, - dtype, - value, - out=None, - main_program=None, - startup_program=None): - """ - This function creates a tensor , with shape as mentioned in the input and - specified dtype and fills this up with a constant value that - comes in the input. It also sets the stop_gradient to be True. - """ - helper = LayerHelper("fill_constant", **locals()) - if out is None: - out = helper.create_tmp_variable(dtype=dtype) - helper.append_op( - type='fill_constant', - inputs={}, - outputs={'Out': [out]}, - attrs={'shape': shape, - 'dtype': out.dtype, - 'value': float(value)}) - out.stop_gradient = True - return out - - -def fill_constant_batch_size_like(input, - shape, - dtype, - value, - input_dim_idx=0, - output_dim_idx=0, - main_program=None, - startup_program=None): - helper = LayerHelper("fill_constant_batch_size_like", **locals()) - out = helper.create_tmp_variable(dtype=dtype) - helper.append_op( - type='fill_constant_batch_size_like', - inputs={'Input': input}, - outputs={'Out': [out]}, - attrs={ - 'shape': shape, - 'dtype': out.dtype, - 'value': float(value), - 'input_dim_idx': input_dim_idx, - 'output_dim_idx': output_dim_idx - }) - out.stop_gradient = True - return out - - -def ones(shape, dtype, main_program=None): - """ - This function performs the same function as fill_constant() declared above - with the constant value being 1.0. - """ - return fill_constant(value=1.0, **locals()) - - -def zeros(shape, dtype, main_program=None): - """ - This function performs the same function as fill_constant() declared above - with the constant value being 0.0. - """ - return fill_constant(value=0.0, **locals()) - - -def increment(x, - value=1.0, - in_place=True, - main_program=None, - startup_program=None): - """ - This function creates an operator to increment each value in the input - `x` by an amount: `value` as mentioned in the input parameter. This - operation is performed in-place by default. - """ - helper = LayerHelper("increment", **locals()) - if not in_place: - out = helper.create_tmp_variable(dtype=x.dtype) - else: - out = x - helper.append_op( - type='increment', - inputs={'X': [x]}, - outputs={'Out': [out]}, - attrs={'step': float(value)}) - return out - - -def array_write(x, i, array=None, main_program=None, startup_program=None): - """ - This function creates an operator to write the data out as a - LOD_TENSOR_ARRAY. - """ - helper = LayerHelper('array_write', **locals()) - if array is None: - array = helper.create_variable( - name="{0}.out".format(helper.name), - type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, - dtype=x.dtype) - helper.append_op( - type='write_to_array', - inputs={'X': [x], - 'I': [i]}, - outputs={'Out': [array]}) - return array - - -def create_array(dtype, main_program=None): - helper = LayerHelper("array", **locals()) - return helper.create_variable( - name="{0}.out".format(helper.name), - type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, - dtype=dtype) - - -def less_than(x, y, cond=None, main_program=None, **ignored): - helper = LayerHelper("less_than", **locals()) - if cond is None: - cond = helper.create_tmp_variable(dtype='bool') - cond.stop_gradient = True - - helper.append_op( - type='less_than', inputs={'X': [x], - 'Y': [y]}, outputs={'Out': [cond]}) - return cond - - -def array_read(array, i, main_program=None, startup_program=None): - """ - This function creates an operator to read the data in as a - LOD_TENSOR_ARRAY. - """ - helper = LayerHelper('array_read', **locals()) - if not isinstance( - array, - Variable) or array.type != core.VarDesc.VarType.LOD_TENSOR_ARRAY: - raise TypeError("array should be tensor array vairable") - out = helper.create_tmp_variable(dtype=array.dtype) - helper.append_op( - type='read_from_array', - inputs={'X': [array], - 'I': [i]}, - outputs={'Out': [out]}) - return out - - -def shrink_memory(x, i, table, main_program=None, startup_program=None): - """ - This function creates an operator to shrink_rnn_memory using the RankTable - as mentioned in the input parameter. - """ - helper = LayerHelper('shrink_memory', **locals()) - out = helper.create_tmp_variable(dtype=x.dtype) - helper.append_op( - type='shrink_rnn_memory', - inputs={'X': [x], - 'I': [i], - 'RankTable': [table]}, - outputs={'Out': [out]}, - attrs={}) - return out - - -def array_length(array, main_program=None): - """ - This function creates an operator to find the length of the - LOD_TENSOR_ARRAY. - """ - helper = LayerHelper('array_length', **locals()) - tmp = helper.create_tmp_variable(dtype='int64') - tmp.stop_gradient = True - helper.append_op( - type='lod_array_length', inputs={'X': [array]}, outputs={'Out': [tmp]}) - return tmp - - -def conv2d_transpose(input, - num_filters, - output_size=None, - filter_size=None, - padding=None, - stride=None, - param_attr=None, - main_program=None, - startup_program=None): - """ - The transpose of conv2d layer. - - This layer is also known as deconvolution layer. - - Args: - input(Variable): The input image with [N, C, H, W] format. - num_filters(int): The number of filter. It is as same as the output - image channel. - output_size(int|tuple|None): The output image size. If output size is a - tuple, it must contain two integers, (image_H, image_W). This - parameter only works when filter_size is None. - filter_size(int|tuple|None): The filter size. If filter_size is a tuple, - it must contain two integers, (filter_size_H, filter_size_W). - Otherwise, the filter will be a square. None if use output size to - calculate filter_size - padding(int|tuple): The padding size. If padding is a tuple, it must - contain two integers, (padding_H, padding_W). Otherwise, the - padding_H = padding_W = padding. - stride(int|tuple): The stride size. If stride is a tuple, it must - contain two integers, (stride_H, stride_W). Otherwise, the - stride_H = stride_W = stride. - param_attr: Parameter Attribute. - main_program(Program): the main program - startup_program(Program): the startup program - - Returns: - Variable: Output image. - """ - helper = LayerHelper("conv2d_transpose", **locals()) - if not isinstance(input, Variable): - raise TypeError("Input of conv2d_transpose must be Variable") - input_channel = input.shape[1] - - op_attr = dict() - - if isinstance(padding, int): - op_attr['paddings'] = [padding, padding] - elif padding is not None: - op_attr['paddings'] = padding - - if isinstance(stride, int): - op_attr['strides'] = stride - elif stride is not None: - op_attr['strides'] = stride - - if filter_size is None: - if output_size is None: - raise ValueError("output_size must be set when filter_size is None") - if isinstance(output_size, int): - output_size = [output_size, output_size] - - padding = op_attr.get('paddings', [0, 0]) - stride = op_attr.get('strides', [1, 1]) - - h_in = input.shape[2] - w_in = input.shape[3] - filter_size_h = output_size[0] - \ - (h_in - 1) * stride[0] + 2 * padding[0] - filter_size_w = output_size[1] - \ - (w_in - 1) * stride[1] + 2 * padding[1] - filter_size = [filter_size_h, filter_size_w] - elif isinstance(filter_size, int): - filter_size = [filter_size, filter_size] - - filter_shape = [input_channel, num_filters] + filter_size - img_filter = helper.create_parameter( - dtype=input.dtype, shape=filter_shape, attr=helper.param_attr) - - out = helper.create_tmp_variable(dtype=input.dtype) - helper.append_op( - type='conv2d_transpose', - inputs={'Input': [input], - 'Filter': [img_filter]}, - outputs={'Output': out}, - attrs=op_attr) - - return out - - -class ConditionalBlockGuard(BlockGuard): - def __init__(self, block): - if not isinstance(block, ConditionalBlock): - raise TypeError("block should be conditional block") - super(ConditionalBlockGuard, self).__init__(block.helper.main_program) - self.block = block - - def __enter__(self): - return super(ConditionalBlockGuard, self).__enter__() - - def __exit__(self, exc_type, exc_val, exc_tb): - self.block.complete() - return super(ConditionalBlockGuard, self).__exit__(exc_type, exc_val, - exc_tb) - - -class ConditionalBlock(object): - def __init__(self, - inputs, - name=None, - main_program=None, - startup_program=None): - for each_input in inputs: - if not isinstance(each_input, Variable): - raise TypeError("Each input should be variable") - self.inputs = inputs - self.helper = LayerHelper( - 'conditional_block', - name=name, - main_program=main_program, - startup_program=startup_program) - - def block(self): - return ConditionalBlockGuard(self) - - def complete(self): - inside_block = self.helper.main_program.current_block() - parent_block = self.helper.main_program.block(inside_block.parent_idx) - - intermediate = set() - params = set() - - for each_op in inside_block.ops: - assert isinstance(each_op, Operator) - for iname in each_op.input_names: - for in_var_name in each_op.input(iname): - if in_var_name not in intermediate: - params.add(in_var_name) - - for oname in each_op.output_names: - for out_var_name in each_op.output(oname): - intermediate.add(out_var_name) - input_set = set([ipt.name for ipt in self.inputs]) - - param_list = [ - parent_block.var(each_name) for each_name in params - if each_name not in input_set - ] - - out_list = [ - parent_block.var(var_name) for var_name in parent_block.vars - if var_name not in intermediate - ] - - step_scope = parent_block.create_var( - type=core.VarDesc.VarType.STEP_SCOPES) - parent_block.append_op( - type='conditional_block', - inputs={ - 'X': self.inputs, - 'Params': param_list, - }, - outputs={'Out': out_list, - 'Scope': [step_scope]}, - attrs={'block': inside_block}) - - -class IfElseBlockGuard(object): - def __init__(self, is_true, ifelse): - if not isinstance(ifelse, IfElse): - raise TypeError("ifelse must be an instance of IfElse class") - - if ifelse.status != IfElse.OUT_IF_ELSE_BLOCKS: - raise ValueError("You cannot invoke IfElse.block() inside a block") - - self.is_true = is_true - self.ie = ifelse - if is_true: - self.cond_block = ifelse.conditional_true_block - else: - self.cond_block = ifelse.conditional_false_block - - if not isinstance(self.cond_block, ConditionalBlock): - raise TypeError("Unexpected situation") - - self.cond_block = self.cond_block.block() - - def __enter__(self): - self.ie.status = IfElse.IN_IF_ELSE_TRUE_BLOCKS if self.is_true else IfElse.IN_IF_ELSE_FALSE_BLOCKS - self.cond_block.__enter__() - - def __exit__(self, exc_type, exc_val, exc_tb): - if not self.cond_block.__exit__(exc_type, exc_val, exc_tb): - # re-raise inside exception - return False - if len(self.ie.output_table[1 if self.is_true else 0]) == 0: - raise ValueError("Must set output inside block") - self.ie.status = IfElse.OUT_IF_ELSE_BLOCKS - - -class IfElse(object): - OUT_IF_ELSE_BLOCKS = 0 - IN_IF_ELSE_TRUE_BLOCKS = 1 - IN_IF_ELSE_FALSE_BLOCKS = 2 - - def __init__(self, cond, name=None, main_program=None, - startup_program=None): - if not isinstance(cond, Variable): - raise TypeError("cond must be a Variable") - self.helper = LayerHelper( - 'ifelse', - name=name, - main_program=main_program, - startup_program=startup_program) - self.cond = cond - self.input_table = {} - self.status = IfElse.OUT_IF_ELSE_BLOCKS - self.conditional_true_block = ConditionalBlock(inputs=[self.cond]) - self.conditional_false_block = ConditionalBlock(inputs=[self.cond]) - self.output_table = ([], []) # (true_outs, false_outs) - - def input(self, x): - if self.status == IfElse.OUT_IF_ELSE_BLOCKS: - raise ValueError("input must in true/false blocks") - if id(x) not in self.input_table: - parent_block = self.parent_block() - out_true = parent_block.create_var( - name=unique_name('ifelse_input' + self.helper.name), - dtype=x.dtype) - - out_false = parent_block.create_var( - name=unique_name('ifelse_input' + self.helper.name), - dtype=x.dtype) - parent_block.append_op( - type='split_lod_tensor', - inputs={ - 'X': x, - 'Mask': self.cond, - }, - outputs={'OutTrue': out_true, - 'OutFalse': out_false}, - attrs={'level': 0}) - self.input_table[id(x)] = (out_true, out_false) - else: - out_true, out_false = self.input_table[id(x)] - - if self.status == IfElse.IN_IF_ELSE_TRUE_BLOCKS: - return out_true - else: - return out_false - - def parent_block(self): - current_block = self.helper.main_program.current_block() - return self.helper.main_program.block(current_block.parent_idx) - - def true_block(self): - return IfElseBlockGuard(True, self) - - def false_block(self): - return IfElseBlockGuard(False, self) - - def output(self, *outs): - if self.status == self.OUT_IF_ELSE_BLOCKS: - raise ValueError("output can only be invoked in the sub-block") - - out_table = self.output_table[1 if self.status == - self.IN_IF_ELSE_TRUE_BLOCKS else 0] - parent_block = self.parent_block() - for each_out in outs: - if not isinstance(each_out, Variable): - raise TypeError("Each output should be a variable") - # create outside tensor - outside_out = parent_block.create_var( - name=unique_name("_".join([self.helper.name, 'output'])), - dtype=each_out.dtype) - out_table.append(outside_out) - - # assign local var to outside - assign( - input=each_out, - output=outside_out, - main_program=self.helper.main_program, - startup_program=self.helper.startup_program) - - def __call__(self): - if self.status != self.OUT_IF_ELSE_BLOCKS: - raise ValueError("IfElse::__call__ must be out of sub-block") - false_len, true_len = map(len, self.output_table) - if false_len == 0 and true_len == 0: - raise ValueError("Must invoke true_block/false_block before " - "__call__") - elif false_len != true_len and false_len != 0 and true_len != 0: - raise ValueError("The output side must be same") - elif false_len == 0 or true_len == 0: - return self.output_table[0 if false_len != 0 else 1] - - # else none of false_len/true_len is zero - # merge together - rlist = [] - for false_var, true_var in zip(*self.output_table): - rlist.append( - merge_lod_tensor( - in_true=true_var, - in_false=false_var, - mask=self.cond, - x=self.cond, - level=0, - main_program=self.helper.main_program, - startup_program=self.helper.startup_program)) - return rlist - - -class DynamicRNN(object): - BEFORE_RNN = 0 - IN_RNN = 1 - AFTER_RNN = 2 - - def __init__(self, name=None, main_program=None, startup_program=None): - self.helper = LayerHelper( - 'dynamic_rnn', - name=name, - main_program=main_program, - startup_program=startup_program) - self.status = DynamicRNN.BEFORE_RNN - self.lod_rank_table = None - self.max_seq_len = None - self.step_idx = None - self.zero_idx = fill_constant(shape=[1], value=0, dtype='int64') - self.mem_dict = dict() - self.output_array = [] - self.outputs = [] - self.cond = self.helper.create_tmp_variable(dtype='bool') - self.cond.stop_gradient = False - self.while_op = While(self.cond) - self.input_array = [] - self.mem_link = [] - - def step_input(self, x): - self._assert_in_rnn_block_("step_input") - if not isinstance(x, Variable): - raise TypeError( - "step_input() can only take a Variable as its input") - parent_block = self._parent_block_() - if self.lod_rank_table is None: - self.lod_rank_table = parent_block.create_var( - name=unique_name('lod_rank_table'), - type=core.VarDesc.VarType.LOD_RANK_TABLE) - self.lod_rank_table.stop_gradient = True - parent_block.append_op( - type='lod_rank_table', - inputs={"X": x}, - outputs={"Out": self.lod_rank_table}) - self.max_seq_len = parent_block.create_var( - name=unique_name('dynamic_rnn_max_seq_len'), dtype='int64') - self.max_seq_len.stop_gradient = False - parent_block.append_op( - type='max_sequence_len', - inputs={'RankTable': self.lod_rank_table}, - outputs={"Out": self.max_seq_len}) - self.cond.stop_gradient = True - parent_block.append_op( - type='less_than', - inputs={'X': self.step_idx, - 'Y': self.max_seq_len}, - outputs={'Out': self.cond}) - - input_array = parent_block.create_var( - name=unique_name('dynamic_rnn_input_array'), - type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, - dtype=x.dtype) - self.input_array.append((input_array, x.dtype)) - parent_block.append_op( - type='lod_tensor_to_array', - inputs={'X': x, - 'RankTable': self.lod_rank_table}, - outputs={'Out': input_array}) - return array_read( - array=input_array, i=self.step_idx, **self.helper.to_kwargs) - - @contextlib.contextmanager - def block(self): - if self.status != DynamicRNN.BEFORE_RNN: - raise ValueError("rnn.block() can only be invoke once") - self.step_idx = fill_constant(shape=[1], dtype='int64', value=0) - self.step_idx.stop_gradient = False - self.status = DynamicRNN.IN_RNN - with self.while_op.block(): - yield - increment( - x=self.step_idx, - value=1.0, - in_place=True, - **self.helper.to_kwargs) - - for new_mem, mem_array in self.mem_link: - array_write( - x=new_mem, - i=self.step_idx, - array=mem_array, - **self.helper.to_kwargs) - - less_than( - x=self.step_idx, - y=self.max_seq_len, - cond=self.cond, - **self.helper.to_kwargs) - - self.status = DynamicRNN.AFTER_RNN - for each_array in self.output_array: - self.outputs.append( - array_to_lod_tensor( - x=each_array, - table=self.lod_rank_table, - **self.helper.to_kwargs)) - - def __call__(self, *args, **kwargs): - if self.status != DynamicRNN.AFTER_RNN: - raise ValueError( - "Dynamic RNN outputs can only be retrieved after rnn block") - if len(self.outputs) == 1: - return self.outputs[0] - else: - return self.outputs - - def memory(self, init=None, shape=None, value=0.0, dtype='float32'): - self._assert_in_rnn_block_('memory') - if init is not None: - if not isinstance(init, Variable): - raise TypeError( - "The input arg `init` of memory() must be a Variable") - parent_block = self._parent_block_() - mem_array = parent_block.create_var( - name=unique_name('dynamic_rnn_mem_array'), - type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, - dtype=init.dtype) - parent_block.append_op( - type='write_to_array', - inputs={'X': init, - 'I': self.zero_idx}, - outputs={'Out': mem_array}) - retv = array_read( - array=mem_array, i=self.step_idx, **self.helper.to_kwargs) - retv = shrink_memory( - x=retv, - i=self.step_idx, - table=self.lod_rank_table, - **self.helper.to_kwargs) - self.mem_dict[retv.name] = mem_array - return retv - else: - if len(self.input_array) == 0: - raise ValueError( - "step_input should be invoked before memory(shape=..., value=...)" - ) - parent_block = self._parent_block_() - init = parent_block.create_var( - name=unique_name('mem_init'), dtype=dtype) - arr, dtype = self.input_array[0] - in0 = parent_block.create_var(name=unique_name('in0'), dtype=dtype) - parent_block.append_op( - type='read_from_array', - inputs={'X': [arr], - 'I': [self.zero_idx]}, - outputs={'Out': [in0]}) - parent_block.append_op( - type='fill_constant_batch_size_like', - inputs={'Input': [in0]}, - outputs={'Out': [init]}, - attrs={ - 'shape': [-1] + shape, - 'value': float(value), - 'dtype': init.dtype - }) - return self.memory(init=init) - - def update_memory(self, ex_mem, new_mem): - self._assert_in_rnn_block_('update_memory') - if not isinstance(ex_mem, Variable): - raise TypeError("The input arg `ex_mem` of update_memory() must " - "be a Variable") - if not isinstance(new_mem, Variable): - raise TypeError("The input arg `new_mem` of update_memory() must " - "be a Variable") - - mem_array = self.mem_dict.get(ex_mem.name, None) - if mem_array is None: - raise ValueError("Please invoke memory before update_memory") - if self.lod_rank_table is None: - raise ValueError("Please invoke step_input before update_memory") - - self.mem_link.append((new_mem, mem_array)) - - def output(self, *outputs): - self._assert_in_rnn_block_('output') - parent_block = self._parent_block_() - for each in outputs: - outside_array = parent_block.create_var( - name=unique_name("_".join( - [self.helper.name, "output_array", each.name])), - type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, - dtype=each.dtype) - array_write(x=each, i=self.step_idx, array=outside_array) - self.output_array.append(outside_array) - - def _parent_block_(self): - prog = self.helper.main_program - parent_idx = prog.current_block().parent_idx - assert parent_idx >= 0 - parent_block = prog.block(parent_idx) - - return parent_block - - def _assert_in_rnn_block_(self, method): - if self.status != DynamicRNN.IN_RNN: - raise ValueError("{0} can only be invoked inside rnn block.".format( - method)) diff --git a/python/paddle/v2/fluid/layers/__init__.py b/python/paddle/v2/fluid/layers/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..249f570e13b7a1b50397fb971d1c6f77e0359a5e --- /dev/null +++ b/python/paddle/v2/fluid/layers/__init__.py @@ -0,0 +1,17 @@ +import ops +from ops import * +import nn +from nn import * +import io +from io import * +import tensor +from tensor import * +import control_flow +from control_flow import * + +__all__ = [] +__all__ += nn.__all__ +__all__ += io.__all__ +__all__ += tensor.__all__ +__all__ += control_flow.__all__ +__all__ += ops.__all__ diff --git a/python/paddle/v2/fluid/layers/control_flow.py b/python/paddle/v2/fluid/layers/control_flow.py new file mode 100644 index 0000000000000000000000000000000000000000..5af6c789773fe80ceed99c69a419f18cf2db8d37 --- /dev/null +++ b/python/paddle/v2/fluid/layers/control_flow.py @@ -0,0 +1,1022 @@ +from ..layer_helper import LayerHelper, unique_name +from ..framework import Program, Variable, Operator +from .. import core +from tensor import assign, fill_constant +import contextlib + +__all__ = [ + 'split_lod_tensor', 'merge_lod_tensor', 'BlockGuard', 'StaticRNNGuard', + 'StaticRNNMemoryLink', 'WhileGuard', 'While', 'lod_rank_table', + 'max_sequence_len', 'topk', 'lod_tensor_to_array', 'array_to_lod_tensor', + 'increment', 'array_write', 'create_array', 'less_than', 'array_read', + 'shrink_memory', 'array_length', 'IfElse', 'DynamicRNN', 'ConditionalBlock', + 'StaticRNN' +] + + +def split_lod_tensor(input, + mask, + level=0, + main_program=None, + startup_program=None): + helper = LayerHelper('split_lod_tensor', **locals()) + out_true = helper.create_tmp_variable(dtype=input.dtype) + out_false = helper.create_tmp_variable(dtype=input.dtype) + helper.append_op( + type='split_lod_tensor', + inputs={ + 'X': input, + 'Mask': mask, + }, + outputs={'OutTrue': out_true, + 'OutFalse': out_false}, + attrs={'level': level}) + return out_true, out_false + + +def merge_lod_tensor(in_true, + in_false, + x, + mask, + level=0, + main_program=None, + startup_program=None): + helper = LayerHelper('merge_lod_tensor', **locals()) + out = helper.create_tmp_variable(dtype=in_true.dtype) + helper.append_op( + type='merge_lod_tensor', + inputs={'X': x, + 'Mask': mask, + 'InTrue': in_true, + 'InFalse': in_false}, + outputs={'Out': out}, + attrs={'level': level}) + return out + + +class BlockGuard(object): + """ + BlockGuard class. + + BlockGuard class is used to create a sub-block in a program by + using the Python `with` keyword. + """ + + def __init__(self, main_program): + if not isinstance(main_program, Program): + raise TypeError("BlockGuard takes a program") + self.main_program = main_program + + def __enter__(self): + self.main_program.create_block() + + def __exit__(self, exc_type, exc_val, exc_tb): + self.main_program.rollback() + if exc_type is not None: + return False # re-raise exception + return True + + +class StaticRNNGuard(BlockGuard): + """ + StaticRNNGuard class. + + StaticRNNGuard class is used to create a StaticRNN block in a program. + """ + + def __init__(self, rnn): + if not isinstance(rnn, StaticRNN): + raise TypeError("StaticRNNGuard takes a StaticRNN") + super(StaticRNNGuard, self).__init__(rnn.helper.main_program) + self.rnn = rnn + + def __enter__(self): + self.rnn.status = StaticRNN.IN_RNN_BLOCK + return super(StaticRNNGuard, self).__enter__() + + def __exit__(self, exc_type, exc_val, exc_tb): + if exc_type is not None: + return False + self.rnn.status = StaticRNN.AFTER_RNN_BLOCK + self.rnn.complete_rnn_op() + return super(StaticRNNGuard, self).__exit__(exc_type, exc_val, exc_tb) + + +class StaticRNNMemoryLink(object): + """ + StaticRNNMemoryLink class. + + Args: + init: the initial variable for Memory + init: Variable + pre_mem: the memory variable in previous time step + pre_mem: Variable + mem: the memory variable in current time step + mem: Variable + + StaticRNNMemoryLink class is used to create a link between two + memory cells of a StaticRNN. + """ + + def __init__(self, init, pre_mem, mem=None): + self.init = init + self.pre_mem = pre_mem + self.mem = mem + + +class StaticRNN(object): + """ + StaticRNN class. + + StaticRNN class is used to create a StaticRNN. The RNN will have its + own parameters like inputs, outputs, memories, status and length. + """ + BEFORE_RNN_BLOCK = 0 + IN_RNN_BLOCK = 1 + AFTER_RNN_BLOCK = 2 + + def __init__(self, name=None, main_program=None): + self.helper = LayerHelper( + "static_rnn", name=name, main_program=main_program) + self.memories = {} # memory map, from pre_mem.name --> MemoryLink + self.inputs = [] # input variable list in current block + self.outputs = [] # output variable list in parent block + self.status = StaticRNN.BEFORE_RNN_BLOCK # status flag. + # sequence length, since it is a static RNN, sequence length are fixed. + self.seq_len = None + + def step(self): + return StaticRNNGuard(self) + + def _assert_in_rnn_block_(self, method): + if self.status != StaticRNN.IN_RNN_BLOCK: + raise ValueError("You must invoke {0} in rnn block".format(method)) + + def memory(self, + init=None, + shape=None, + batch_ref=None, + init_value=0.0, + init_batch_dim_idx=0, + ref_batch_dim_idx=1): + """ + Args: + init: boot memory, if not set, a shape, batch_ref must be provided + shape: shape of the boot memory + batch_ref: batch size reference variable + init_value: the init value of boot memory + init_batch_dim_idx: the index of batch size in init's dimension + ref_batch_dim_idx: the index of batch size in batch_ref's dimension + """ + self._assert_in_rnn_block_('memory') + if init is None: + if shape is None or batch_ref is None: + raise ValueError( + "if init is None, memory at least need shape and batch_ref") + parent_block = self.parent_block() + var_name = unique_name("@".join([self.helper.name, "memory_boot"])) + boot_var = parent_block.create_var( + name=var_name, + shape=shape, + dtype=batch_ref.dtype, + persistable=False) + + parent_block.append_op( + type="fill_constant_batch_size_like", + inputs={'Input': [batch_ref]}, + outputs={'Out': [boot_var]}, + attrs={ + 'value': init_value, + 'shape': boot_var.shape, + 'dtype': boot_var.dtype, + 'input_dim_idx': ref_batch_dim_idx, + 'output_dim_idx': init_batch_dim_idx + }) + + return self.memory(init=boot_var) + else: + pre_mem = self.helper.create_variable( + name=unique_name("@".join([self.helper.name, "mem"])), + dtype=init.dtype, + shape=init.shape) + self.memories[pre_mem.name] = StaticRNNMemoryLink( + init=init, pre_mem=pre_mem) + return pre_mem + + def step_input(self, x): + self._assert_in_rnn_block_('step_input') + if not isinstance(x, Variable): + raise TypeError("step input takes a Variable") + if self.seq_len is None: + self.seq_len = x.shape[0] + elif self.seq_len != x.shape[0]: + raise ValueError("Static RNN only take fix seq_len input") + + ipt = self.helper.create_variable( + name=x.name, dtype=x.dtype, shape=list(x.shape[1:]), type=x.type) + self.inputs.append(ipt) + return ipt + + def step_output(self, o): + self._assert_in_rnn_block_('step_output') + if not isinstance(o, Variable): + raise TypeError("step output takes a Variable") + + tmp_o = self.helper.create_tmp_variable(dtype=o.dtype) + self.helper.append_op( + type='rnn_memory_helper', + inputs={'X': [o]}, + outputs={'Out': tmp_o}, + attrs={'dtype': o.dtype}) + + out_var = self.parent_block().create_var( + name=tmp_o.name, + shape=[self.seq_len] + list(tmp_o.shape), + dtype=tmp_o.dtype) + + self.outputs.append(out_var) + + def output(self, *outputs): + for each in outputs: + self.step_output(each) + + def update_memory(self, mem, var): + if not isinstance(mem, Variable) or not isinstance(var, Variable): + raise TypeError("update memory should take variables") + self.memories[mem.name].mem = var + + def parent_block(self): + prog = self.helper.main_program + parent_idx = prog.current_block().parent_idx + assert parent_idx >= 0 + parent_block = prog.block(parent_idx) + return parent_block + + def __call__(self, *args, **kwargs): + if self.status != StaticRNN.AFTER_RNN_BLOCK: + raise ValueError("RNN output can only be retrieved after rnn block") + if len(self.outputs) == 0: + raise ValueError("RNN has no output") + elif len(self.outputs) == 1: + return self.outputs[0] + else: + return self.outputs + + def complete_rnn_op(self): + main_program = self.helper.main_program + rnn_block = main_program.current_block() + parent_block = self.parent_block() + + local_inputs = set() + + for op in rnn_block.ops: + assert isinstance(op, Operator) + for oname in op.output_names: + for out_var_name in op.output(oname): + local_inputs.add(out_var_name) + + for var in self.inputs: + local_inputs.add(var.name) + for m in self.memories: + local_inputs.add(m) + + params = list() + for op in rnn_block.ops: + assert isinstance(op, Operator) + for iname in op.input_names: + for in_var_name in op.input(iname): + if in_var_name not in local_inputs: + params.append(in_var_name) + + parameters = [parent_block.var(name) for name in params] + + step_scope = parent_block.create_var( + type=core.VarDesc.VarType.STEP_SCOPES) + + inlinks = [parent_block.var(i.name) for i in self.inputs] + outlinks = self.outputs + + boot_memories = [] + pre_memories = [] + memories = [] + for _, mem in self.memories.iteritems(): + boot_memories.append(mem.init) + pre_memories.append(mem.pre_mem.name) + mem_var = rnn_block.var(mem.mem.name) + assert isinstance(mem_var, Variable) + new_mem = self.helper.create_tmp_variable(dtype=mem_var.dtype) + + rnn_block.append_op( + type='rnn_memory_helper', + inputs={'X': [mem_var]}, + outputs={'Out': [new_mem]}, + attrs={'dtype': mem_var.dtype}) + + memories.append(new_mem.name) + + parent_block.append_op( + type='recurrent', + inputs={ + 'inputs': inlinks, + 'initial_states': boot_memories, + 'parameters': parameters + }, + outputs={'outputs': outlinks, + 'step_scopes': [step_scope]}, + attrs={ + 'ex_states': pre_memories, + 'states': memories, + 'sub_block': rnn_block + }) + + +class WhileGuard(BlockGuard): + def __init__(self, while_op): + if not isinstance(while_op, While): + raise TypeError("WhileGuard takes a while op") + super(WhileGuard, self).__init__(while_op.helper.main_program) + self.while_op = while_op + + def __enter__(self): + self.while_op.status = While.IN_WHILE_BLOCK + return super(WhileGuard, self).__enter__() + + def __exit__(self, exc_type, exc_val, exc_tb): + if exc_type is not None: + return False + self.while_op.status = While.AFTER_WHILE_BLOCK + self.while_op.complete() + return super(WhileGuard, self).__exit__(exc_type, exc_val, exc_tb) + + +class While(object): + BEFORE_WHILE_BLOCK = 0 + IN_WHILE_BLOCK = 1 + AFTER_WHILE_BLOCK = 2 + + def __init__(self, cond, name=None, main_program=None): + self.helper = LayerHelper("while", name=name, main_program=main_program) + self.status = While.BEFORE_WHILE_BLOCK + if not isinstance(cond, Variable): + raise TypeError("condition should be a variable") + assert isinstance(cond, Variable) + if cond.dtype != core.DataType.BOOL: + raise TypeError("condition should be a bool variable") + if reduce(lambda a, b: a * b, cond.shape, 1) != 1: + raise TypeError("condition should be a bool scalar") + self.cond_var = cond + + def block(self): + return WhileGuard(self) + + def complete(self): + main_program = self.helper.main_program + while_block = main_program.current_block() + parent_block = main_program.block(main_program.current_block() + .parent_idx) + + inner_outputs = {self.cond_var.name} + x_name_list = set() + for op in while_block.ops: + for iname in op.input_names: + for in_var_name in op.input(iname): + if in_var_name not in inner_outputs: + x_name_list.add(in_var_name) + + for oname in op.output_names: + for out_var_name in op.output(oname): + inner_outputs.add(out_var_name) + + out_vars = [] + for inner_out_name in inner_outputs: + if inner_out_name in parent_block.vars: + out_vars.append(parent_block.var(inner_out_name)) + + step_scope = parent_block.create_var( + type=core.VarDesc.VarType.STEP_SCOPES) + + parent_block.append_op( + type='while', + inputs={ + 'X': [parent_block.var(x_name) for x_name in x_name_list], + 'Condition': [self.cond_var] + }, + outputs={'Out': out_vars, + 'StepScopes': [step_scope]}, + attrs={'sub_block': while_block}) + + +def lod_rank_table(x, level=0, main_program=None): + """ + This function creates an operator for creating a LOD_RANK_TABLE + using the input x. + """ + helper = LayerHelper("lod_rank_table", **locals()) + table = helper.create_variable( + type=core.VarDesc.VarType.LOD_RANK_TABLE, + name=unique_name("lod_rank_table")) + helper.append_op( + type='lod_rank_table', + inputs={'X': x}, + outputs={'Out': table}, + attrs={'level': level}) + return table + + +def max_sequence_len(rank_table, main_program=None): + """ + This function creates an operator to calculate the length of + max seqence through input rank_table(should be a lod_rank_table) + """ + helper = LayerHelper("max_seqence_len", **locals()) + res = helper.create_tmp_variable(dtype="int64") + helper.append_op( + type="max_sequence_len", + inputs={"RankTable": rank_table}, + outputs={"Out": res}) + return res + + +def topk(input, k, main_program=None, startup_program=None): + helper = LayerHelper('topk', **locals()) + topk_out = helper.create_tmp_variable(dtype=input.data_type) + topk_indices = helper.create_tmp_variable(dtype='int64') + helper.append_op( + type='top_k', + inputs={'X': [input]}, + outputs={'Out': [topk_out], + 'Indices': [topk_indices]}, + attrs={'k': k}) + return topk_out, topk_indices + + +def lod_tensor_to_array(x, table, main_program=None): + """ + This function creates an operator to convert an LOD_Tensor to + an array. + """ + helper = LayerHelper("lod_tensor_to_array", **locals()) + array = helper.create_variable( + name=unique_name("lod_tensor_to_array"), + type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, + dtype=x.dtype) + helper.append_op( + type='lod_tensor_to_array', + inputs={'X': x, + 'RankTable': table}, + outputs={'Out': array}) + return array + + +def array_to_lod_tensor(x, table, main_program=None, startup_program=None): + """ + This function creates an operator to convert an array to a + LOD_Tensor. + """ + helper = LayerHelper("array_to_lod_tensor", **locals()) + tmp = helper.create_tmp_variable(dtype=x.dtype) + helper.append_op( + type="array_to_lod_tensor", + inputs={'X': x, + 'RankTable': table}, + outputs={'Out': tmp}) + return tmp + + +def increment(x, + value=1.0, + in_place=True, + main_program=None, + startup_program=None): + """ + This function creates an operator to increment each value in the input + `x` by an amount: `value` as mentioned in the input parameter. This + operation is performed in-place by default. + """ + helper = LayerHelper("increment", **locals()) + if not in_place: + out = helper.create_tmp_variable(dtype=x.dtype) + else: + out = x + helper.append_op( + type='increment', + inputs={'X': [x]}, + outputs={'Out': [out]}, + attrs={'step': float(value)}) + return out + + +def array_write(x, i, array=None, main_program=None, startup_program=None): + """ + This function creates an operator to write the data out as a + LOD_TENSOR_ARRAY. + """ + helper = LayerHelper('array_write', **locals()) + if array is None: + array = helper.create_variable( + name="{0}.out".format(helper.name), + type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, + dtype=x.dtype) + helper.append_op( + type='write_to_array', + inputs={'X': [x], + 'I': [i]}, + outputs={'Out': [array]}) + return array + + +def create_array(dtype, main_program=None): + helper = LayerHelper("array", **locals()) + return helper.create_variable( + name="{0}.out".format(helper.name), + type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, + dtype=dtype) + + +def less_than(x, y, cond=None, main_program=None, **ignored): + helper = LayerHelper("less_than", **locals()) + if cond is None: + cond = helper.create_tmp_variable(dtype='bool') + cond.stop_gradient = True + + helper.append_op( + type='less_than', inputs={'X': [x], + 'Y': [y]}, outputs={'Out': [cond]}) + return cond + + +def array_read(array, i, main_program=None, startup_program=None): + """ + This function creates an operator to read the data in as a + LOD_TENSOR_ARRAY. + """ + helper = LayerHelper('array_read', **locals()) + if not isinstance( + array, + Variable) or array.type != core.VarDesc.VarType.LOD_TENSOR_ARRAY: + raise TypeError("array should be tensor array vairable") + out = helper.create_tmp_variable(dtype=array.dtype) + helper.append_op( + type='read_from_array', + inputs={'X': [array], + 'I': [i]}, + outputs={'Out': [out]}) + return out + + +def shrink_memory(x, i, table, main_program=None, startup_program=None): + """ + This function creates an operator to shrink_rnn_memory using the RankTable + as mentioned in the input parameter. + """ + helper = LayerHelper('shrink_memory', **locals()) + out = helper.create_tmp_variable(dtype=x.dtype) + helper.append_op( + type='shrink_rnn_memory', + inputs={'X': [x], + 'I': [i], + 'RankTable': [table]}, + outputs={'Out': [out]}, + attrs={}) + return out + + +def array_length(array, main_program=None): + """ + This function creates an operator to find the length of the + LOD_TENSOR_ARRAY. + """ + helper = LayerHelper('array_length', **locals()) + tmp = helper.create_tmp_variable(dtype='int64') + tmp.stop_gradient = True + helper.append_op( + type='lod_array_length', inputs={'X': [array]}, outputs={'Out': [tmp]}) + return tmp + + +class ConditionalBlockGuard(BlockGuard): + def __init__(self, block): + if not isinstance(block, ConditionalBlock): + raise TypeError("block should be conditional block") + super(ConditionalBlockGuard, self).__init__(block.helper.main_program) + self.block = block + + def __enter__(self): + return super(ConditionalBlockGuard, self).__enter__() + + def __exit__(self, exc_type, exc_val, exc_tb): + self.block.complete() + return super(ConditionalBlockGuard, self).__exit__(exc_type, exc_val, + exc_tb) + + +class ConditionalBlock(object): + def __init__(self, + inputs, + name=None, + main_program=None, + startup_program=None): + for each_input in inputs: + if not isinstance(each_input, Variable): + raise TypeError("Each input should be variable") + self.inputs = inputs + self.helper = LayerHelper( + 'conditional_block', + name=name, + main_program=main_program, + startup_program=startup_program) + + def block(self): + return ConditionalBlockGuard(self) + + def complete(self): + inside_block = self.helper.main_program.current_block() + parent_block = self.helper.main_program.block(inside_block.parent_idx) + + intermediate = set() + params = set() + + for each_op in inside_block.ops: + assert isinstance(each_op, Operator) + for iname in each_op.input_names: + for in_var_name in each_op.input(iname): + if in_var_name not in intermediate: + params.add(in_var_name) + + for oname in each_op.output_names: + for out_var_name in each_op.output(oname): + intermediate.add(out_var_name) + input_set = set([ipt.name for ipt in self.inputs]) + + param_list = [ + parent_block.var(each_name) for each_name in params + if each_name not in input_set + ] + + out_list = [ + parent_block.var(var_name) for var_name in parent_block.vars + if var_name not in intermediate + ] + + step_scope = parent_block.create_var( + type=core.VarDesc.VarType.STEP_SCOPES) + parent_block.append_op( + type='conditional_block', + inputs={ + 'X': self.inputs, + 'Params': param_list, + }, + outputs={'Out': out_list, + 'Scope': [step_scope]}, + attrs={'sub_block': inside_block}) + + +class IfElseBlockGuard(object): + def __init__(self, is_true, ifelse): + if not isinstance(ifelse, IfElse): + raise TypeError("ifelse must be an instance of IfElse class") + + if ifelse.status != IfElse.OUT_IF_ELSE_BLOCKS: + raise ValueError("You cannot invoke IfElse.block() inside a block") + + self.is_true = is_true + self.ie = ifelse + if is_true: + self.cond_block = ifelse.conditional_true_block + else: + self.cond_block = ifelse.conditional_false_block + + if not isinstance(self.cond_block, ConditionalBlock): + raise TypeError("Unexpected situation") + + self.cond_block = self.cond_block.block() + + def __enter__(self): + self.ie.status = IfElse.IN_IF_ELSE_TRUE_BLOCKS if self.is_true else IfElse.IN_IF_ELSE_FALSE_BLOCKS + self.cond_block.__enter__() + + def __exit__(self, exc_type, exc_val, exc_tb): + if not self.cond_block.__exit__(exc_type, exc_val, exc_tb): + # re-raise inside exception + return False + if len(self.ie.output_table[1 if self.is_true else 0]) == 0: + raise ValueError("Must set output inside block") + self.ie.status = IfElse.OUT_IF_ELSE_BLOCKS + + +class IfElse(object): + OUT_IF_ELSE_BLOCKS = 0 + IN_IF_ELSE_TRUE_BLOCKS = 1 + IN_IF_ELSE_FALSE_BLOCKS = 2 + + def __init__(self, cond, name=None, main_program=None, + startup_program=None): + if not isinstance(cond, Variable): + raise TypeError("cond must be a Variable") + self.helper = LayerHelper( + 'ifelse', + name=name, + main_program=main_program, + startup_program=startup_program) + self.cond = cond + self.input_table = {} + self.status = IfElse.OUT_IF_ELSE_BLOCKS + self.conditional_true_block = ConditionalBlock(inputs=[self.cond]) + self.conditional_false_block = ConditionalBlock(inputs=[self.cond]) + self.output_table = ([], []) # (true_outs, false_outs) + + def input(self, x): + if self.status == IfElse.OUT_IF_ELSE_BLOCKS: + raise ValueError("input must in true/false blocks") + if id(x) not in self.input_table: + parent_block = self.parent_block() + out_true = parent_block.create_var( + name=unique_name('ifelse_input' + self.helper.name), + dtype=x.dtype) + + out_false = parent_block.create_var( + name=unique_name('ifelse_input' + self.helper.name), + dtype=x.dtype) + parent_block.append_op( + type='split_lod_tensor', + inputs={ + 'X': x, + 'Mask': self.cond, + }, + outputs={'OutTrue': out_true, + 'OutFalse': out_false}, + attrs={'level': 0}) + self.input_table[id(x)] = (out_true, out_false) + else: + out_true, out_false = self.input_table[id(x)] + + if self.status == IfElse.IN_IF_ELSE_TRUE_BLOCKS: + return out_true + else: + return out_false + + def parent_block(self): + current_block = self.helper.main_program.current_block() + return self.helper.main_program.block(current_block.parent_idx) + + def true_block(self): + return IfElseBlockGuard(True, self) + + def false_block(self): + return IfElseBlockGuard(False, self) + + def output(self, *outs): + if self.status == self.OUT_IF_ELSE_BLOCKS: + raise ValueError("output can only be invoked in the sub-block") + + out_table = self.output_table[1 if self.status == + self.IN_IF_ELSE_TRUE_BLOCKS else 0] + parent_block = self.parent_block() + for each_out in outs: + if not isinstance(each_out, Variable): + raise TypeError("Each output should be a variable") + # create outside tensor + outside_out = parent_block.create_var( + name=unique_name("_".join([self.helper.name, 'output'])), + dtype=each_out.dtype) + out_table.append(outside_out) + + # assign local var to outside + assign( + input=each_out, + output=outside_out, + main_program=self.helper.main_program, + startup_program=self.helper.startup_program) + + def __call__(self): + if self.status != self.OUT_IF_ELSE_BLOCKS: + raise ValueError("IfElse::__call__ must be out of sub-block") + false_len, true_len = map(len, self.output_table) + if false_len == 0 and true_len == 0: + raise ValueError("Must invoke true_block/false_block before " + "__call__") + elif false_len != true_len and false_len != 0 and true_len != 0: + raise ValueError("The output side must be same") + elif false_len == 0 or true_len == 0: + return self.output_table[0 if false_len != 0 else 1] + + # else none of false_len/true_len is zero + # merge together + rlist = [] + for false_var, true_var in zip(*self.output_table): + rlist.append( + merge_lod_tensor( + in_true=true_var, + in_false=false_var, + mask=self.cond, + x=self.cond, + level=0, + main_program=self.helper.main_program, + startup_program=self.helper.startup_program)) + return rlist + + +class DynamicRNN(object): + BEFORE_RNN = 0 + IN_RNN = 1 + AFTER_RNN = 2 + + def __init__(self, name=None, main_program=None, startup_program=None): + self.helper = LayerHelper( + 'dynamic_rnn', + name=name, + main_program=main_program, + startup_program=startup_program) + self.status = DynamicRNN.BEFORE_RNN + self.lod_rank_table = None + self.max_seq_len = None + self.step_idx = None + self.zero_idx = fill_constant(shape=[1], value=0, dtype='int64') + self.mem_dict = dict() + self.output_array = [] + self.outputs = [] + self.cond = self.helper.create_tmp_variable(dtype='bool') + self.cond.stop_gradient = False + self.while_op = While(self.cond) + self.input_array = [] + self.mem_link = [] + + def step_input(self, x): + self._assert_in_rnn_block_("step_input") + if not isinstance(x, Variable): + raise TypeError( + "step_input() can only take a Variable as its input") + parent_block = self._parent_block_() + if self.lod_rank_table is None: + self.lod_rank_table = parent_block.create_var( + name=unique_name('lod_rank_table'), + type=core.VarDesc.VarType.LOD_RANK_TABLE) + self.lod_rank_table.stop_gradient = True + parent_block.append_op( + type='lod_rank_table', + inputs={"X": x}, + outputs={"Out": self.lod_rank_table}) + self.max_seq_len = parent_block.create_var( + name=unique_name('dynamic_rnn_max_seq_len'), dtype='int64') + self.max_seq_len.stop_gradient = False + parent_block.append_op( + type='max_sequence_len', + inputs={'RankTable': self.lod_rank_table}, + outputs={"Out": self.max_seq_len}) + self.cond.stop_gradient = True + parent_block.append_op( + type='less_than', + inputs={'X': self.step_idx, + 'Y': self.max_seq_len}, + outputs={'Out': self.cond}) + + input_array = parent_block.create_var( + name=unique_name('dynamic_rnn_input_array'), + type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, + dtype=x.dtype) + self.input_array.append((input_array, x.dtype)) + parent_block.append_op( + type='lod_tensor_to_array', + inputs={'X': x, + 'RankTable': self.lod_rank_table}, + outputs={'Out': input_array}) + return array_read( + array=input_array, i=self.step_idx, **self.helper.to_kwargs) + + @contextlib.contextmanager + def block(self): + if self.status != DynamicRNN.BEFORE_RNN: + raise ValueError("rnn.block() can only be invoke once") + self.step_idx = fill_constant(shape=[1], dtype='int64', value=0) + self.step_idx.stop_gradient = False + self.status = DynamicRNN.IN_RNN + with self.while_op.block(): + yield + increment( + x=self.step_idx, + value=1.0, + in_place=True, + **self.helper.to_kwargs) + + for new_mem, mem_array in self.mem_link: + array_write( + x=new_mem, + i=self.step_idx, + array=mem_array, + **self.helper.to_kwargs) + + less_than( + x=self.step_idx, + y=self.max_seq_len, + cond=self.cond, + **self.helper.to_kwargs) + + self.status = DynamicRNN.AFTER_RNN + for each_array in self.output_array: + self.outputs.append( + array_to_lod_tensor( + x=each_array, + table=self.lod_rank_table, + **self.helper.to_kwargs)) + + def __call__(self, *args, **kwargs): + if self.status != DynamicRNN.AFTER_RNN: + raise ValueError( + "Dynamic RNN outputs can only be retrieved after rnn block") + if len(self.outputs) == 1: + return self.outputs[0] + else: + return self.outputs + + def memory(self, init=None, shape=None, value=0.0, dtype='float32'): + self._assert_in_rnn_block_('memory') + if init is not None: + if not isinstance(init, Variable): + raise TypeError( + "The input arg `init` of memory() must be a Variable") + parent_block = self._parent_block_() + mem_array = parent_block.create_var( + name=unique_name('dynamic_rnn_mem_array'), + type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, + dtype=init.dtype) + parent_block.append_op( + type='write_to_array', + inputs={'X': init, + 'I': self.zero_idx}, + outputs={'Out': mem_array}) + retv = array_read( + array=mem_array, i=self.step_idx, **self.helper.to_kwargs) + retv = shrink_memory( + x=retv, + i=self.step_idx, + table=self.lod_rank_table, + **self.helper.to_kwargs) + self.mem_dict[retv.name] = mem_array + return retv + else: + if len(self.input_array) == 0: + raise ValueError( + "step_input should be invoked before memory(shape=..., value=...)" + ) + parent_block = self._parent_block_() + init = parent_block.create_var( + name=unique_name('mem_init'), dtype=dtype) + arr, dtype = self.input_array[0] + in0 = parent_block.create_var(name=unique_name('in0'), dtype=dtype) + parent_block.append_op( + type='read_from_array', + inputs={'X': [arr], + 'I': [self.zero_idx]}, + outputs={'Out': [in0]}) + parent_block.append_op( + type='fill_constant_batch_size_like', + inputs={'Input': [in0]}, + outputs={'Out': [init]}, + attrs={ + 'shape': [-1] + shape, + 'value': float(value), + 'dtype': init.dtype + }) + return self.memory(init=init) + + def update_memory(self, ex_mem, new_mem): + self._assert_in_rnn_block_('update_memory') + if not isinstance(ex_mem, Variable): + raise TypeError("The input arg `ex_mem` of update_memory() must " + "be a Variable") + if not isinstance(new_mem, Variable): + raise TypeError("The input arg `new_mem` of update_memory() must " + "be a Variable") + + mem_array = self.mem_dict.get(ex_mem.name, None) + if mem_array is None: + raise ValueError("Please invoke memory before update_memory") + if self.lod_rank_table is None: + raise ValueError("Please invoke step_input before update_memory") + + self.mem_link.append((new_mem, mem_array)) + + def output(self, *outputs): + self._assert_in_rnn_block_('output') + parent_block = self._parent_block_() + for each in outputs: + outside_array = parent_block.create_var( + name=unique_name("_".join( + [self.helper.name, "output_array", each.name])), + type=core.VarDesc.VarType.LOD_TENSOR_ARRAY, + dtype=each.dtype) + array_write(x=each, i=self.step_idx, array=outside_array) + self.output_array.append(outside_array) + + def _parent_block_(self): + prog = self.helper.main_program + parent_idx = prog.current_block().parent_idx + assert parent_idx >= 0 + parent_block = prog.block(parent_idx) + + return parent_block + + def _assert_in_rnn_block_(self, method): + if self.status != DynamicRNN.IN_RNN: + raise ValueError("{0} can only be invoked inside rnn block.".format( + method)) diff --git a/python/paddle/v2/fluid/layers/io.py b/python/paddle/v2/fluid/layers/io.py new file mode 100644 index 0000000000000000000000000000000000000000..f03d8e3c3e8797619adf837b28ed66ece7db295e --- /dev/null +++ b/python/paddle/v2/fluid/layers/io.py @@ -0,0 +1,57 @@ +from .. import core +from ..layer_helper import LayerHelper + +__all__ = ['data'] + + +def data(name, + shape, + append_batch_size=True, + dtype='float32', + lod_level=0, + type=core.VarDesc.VarType.LOD_TENSOR, + main_program=None, + startup_program=None, + stop_gradient=True): + """ + Data Layer. + + Args: + name: The name/alias of the function + shape: Tuple declaring the shape. + append_batch_size: Whether or not to append the data as a batch. + dtype: The type of data : float32, float_16, int etc + type: The output type. By default it is LOD_TENSOR. + lod_level(int): The LoD Level. 0 means the input data is not a sequence. + main_program: Name of the main program that calls this + startup_program: Name of the startup program + stop_gradient: A boolean that mentions whether gradient should flow. + + This function takes in input and based on whether data has + to be returned back as a minibatch, it creates the global variable using + the helper functions. The global variables can be accessed by all the + following operations and layers in the graph. + + All the input variables of this function are passed in as local variables + to the LayerHelper constructor. + + """ + helper = LayerHelper('data', **locals()) + shape = list(shape) + for i in xrange(len(shape)): + if shape[i] is None: + shape[i] = -1 + append_batch_size = False + elif shape[i] < 0: + append_batch_size = False + + if append_batch_size: + shape = [-1] + shape # append batch size as -1 + + return helper.create_global_variable( + name=name, + shape=shape, + dtype=dtype, + type=type, + stop_gradient=stop_gradient, + lod_level=lod_level) diff --git a/python/paddle/v2/fluid/layers/nn.py b/python/paddle/v2/fluid/layers/nn.py new file mode 100644 index 0000000000000000000000000000000000000000..bad7dbd84e8810db5142a79346cce33eb3c9c8b5 --- /dev/null +++ b/python/paddle/v2/fluid/layers/nn.py @@ -0,0 +1,791 @@ +""" +All layers just related to the neural network. +""" + +from ..layer_helper import LayerHelper +from ..initializer import Normal, Constant +from ..framework import Variable + +__all__ = [ + 'fc', 'embedding', 'dynamic_lstm', 'gru_unit', 'linear_chain_crf', + 'crf_decoding', 'cos_sim', 'cross_entropy', 'square_error_cost', 'accuracy', + 'chunk_eval', 'sequence_conv', 'conv2d', 'sequence_pool', 'pool2d', + 'batch_norm', 'beam_search_decode', 'conv2d_transpose' +] + + +def fc(input, + size, + num_flatten_dims=1, + param_attr=None, + bias_attr=None, + act=None, + name=None, + main_program=None, + startup_program=None): + """ + Fully Connected Layer. + + Args: + input: The input tensor to the function + size: The size of the layer + num_flatten_dims: Number of columns in input + param_attr: The parameters/weights to the FC Layer + param_initializer: Initializer used for the weight/parameter. If None, XavierInitializer() is used + bias_attr: The bias parameter for the FC layer + bias_initializer: Initializer used for the bias. If None, then ConstantInitializer() is used + act: Activation to be applied to the output of FC layer + name: Name/alias of the function + main_program: Name of the main program that calls this + startup_program: Name of the startup program + + This function can take in multiple inputs and performs the Fully Connected + function (linear transformation) on top of each of them. + So for input x, the output will be : Wx + b. Where W is the parameter, + b the bias and x is the input. + + The function also applies an activation (non-linearity) on top of the + output, if activation is passed in the input. + + All the input variables of this function are passed in as local variables + to the LayerHelper constructor. + + """ + helper = LayerHelper('fc', **locals()) + + dtype = helper.input_dtype() + + mul_results = [] + for input_var, param_attr in helper.iter_inputs_and_params(): + input_shape = input_var.shape + param_shape = [ + reduce(lambda a, b: a * b, input_shape[num_flatten_dims:], 1) + ] + [size] + w = helper.create_parameter( + attr=param_attr, shape=param_shape, dtype=dtype, is_bias=False) + tmp = helper.create_tmp_variable(dtype) + helper.append_op( + type="mul", + inputs={ + "X": input_var, + "Y": w, + }, + outputs={"Out": tmp}, + attrs={'x_num_col_dims': num_flatten_dims, + 'y_num_col_dims': 1}) + mul_results.append(tmp) + + # sum + if len(mul_results) == 1: + pre_bias = mul_results[0] + else: + pre_bias = helper.create_tmp_variable(dtype) + helper.append_op( + type="sum", inputs={"X": mul_results}, outputs={"Out": pre_bias}) + # add bias + pre_activation = helper.append_bias_op(pre_bias) + # add activation + return helper.append_activation(pre_activation) + + +def embedding(input, + size, + is_sparse=False, + param_attr=None, + dtype='float32', + main_program=None, + startup_program=None): + """ + Embedding Layer. + + Args: + param_initializer: + input: The input to the function + size: The size of the layer + is_sparse: A flag that decleares whether the input is sparse + param_attr: Parameters for this layer + dtype: The type of data : float32, float_16, int etc + main_program: Name of the main program that calls this + startup_program: Name of the startup program + + This function can take in the input (which is a vector of IDs) and + performs a lookup in the lookup_table using these IDs, to result into + the embedding of each ID in the input. + + All the input variables of this function are passed in as local variables + to the LayerHelper constructor. + + """ + + helper = LayerHelper('embedding', **locals()) + w = helper.create_parameter( + attr=helper.param_attr, shape=size, dtype=dtype, is_bias=False) + tmp = helper.create_tmp_variable(dtype) + helper.append_op( + type='lookup_table', + inputs={'Ids': input, + 'W': w}, + outputs={'Out': tmp}, + attrs={'is_sparse': is_sparse}) + return tmp + + +# TODO(qijun): expose H0 and C0 +def dynamic_lstm(input, + size, + param_attr=None, + bias_attr=None, + use_peepholes=True, + is_reverse=False, + gate_activation='sigmoid', + cell_activation='tanh', + candidate_activation='tanh', + dtype='float32', + main_program=None, + startup_program=None): + helper = LayerHelper('lstm', **locals()) + size = size / 4 + weight = helper.create_parameter( + attr=helper.param_attr, shape=[size, 4 * size], dtype=dtype) + bias_size = [1, 7 * size] + if not use_peepholes: + bias_size[1] = 4 * size + bias = helper.create_parameter( + attr=helper.bias_attr, shape=bias_size, dtype=dtype, is_bias=True) + + hidden = helper.create_tmp_variable(dtype) + cell = helper.create_tmp_variable(dtype) + batch_gate = helper.create_tmp_variable(dtype) + batch_cell_pre_act = helper.create_tmp_variable(dtype) + + helper.append_op( + type='lstm', + inputs={'Input': input, + 'Weight': weight, + 'Bias': bias}, + outputs={ + 'Hidden': hidden, + 'Cell': cell, + 'BatchGate': batch_gate, + 'BatchCellPreAct': batch_cell_pre_act + }, + attrs={ + 'use_peepholes': use_peepholes, + 'is_reverse': is_reverse, + 'gate_activation': gate_activation, + 'cell_activation': cell_activation, + 'candidate_activation': candidate_activation + }) + return hidden, cell + + +def gru_unit(input, + hidden, + size, + weight=None, + bias=None, + activation='tanh', + gate_activation='sigmoid', + main_program=None, + startup_program=None): + """ + GRUUnit Operator implements partial calculations of the GRU unit as following: + + $$ + update \ gate: u_t = actGate(xu_t + W_u * h_{t-1} + b_u) \\ + reset \ gate: r_t = actGate(xr_t + W_r * h_{t-1} + b_r) \\ + output \ candidate: {h}_t = actNode(xc_t + W_c * dot(r_t, h_{t-1}) + b_c) \\ + output: h_t = dot((1 - u_t), h_{t-1}) + dot(u_t, {h}_t) + $$ + + which is same as one time step of GRU Operator. + + @note To implement the complete GRU unit, fully-connected operator must be + used before to feed xu, xr and xc as the Input of GRUUnit operator. + + TODO(ChunweiYan) add more document here + """ + activation_dict = dict( + identity=0, + sigmoid=1, + tanh=2, + relu=3, ) + activation = activation_dict[activation] + gate_activation = activation_dict[gate_activation] + + helper = LayerHelper('gru_unit', **locals()) + dtype = helper.input_dtype() + size = size / 3 + + # create weight + if weight is None: + weight = helper.create_parameter( + attr=helper.param_attr, shape=[size, 3 * size], dtype=dtype) + + # create bias + if bias is None: + bias_size = [1, 3 * size] + bias = helper.create_parameter( + attr=helper.bias_attr, shape=bias_size, dtype=dtype, is_bias=True) + + gate = helper.create_tmp_variable(dtype) + reset_hidden_pre = helper.create_tmp_variable(dtype) + updated_hidden = helper.create_tmp_variable(dtype) + + helper.append_op( + type='gru_unit', + inputs={'Input': input, + 'HiddenPrev': hidden, + 'Weight': weight}, + outputs={ + 'Gate': gate, + 'ResetHiddenPrev': reset_hidden_pre, + 'Hidden': updated_hidden, + }, + attrs={ + 'activation': 0, + 'gate_activation': 1, + }) + + return updated_hidden, reset_hidden_pre, gate + + +def linear_chain_crf(input, + label, + param_attr=None, + main_program=None, + startup_program=None): + helper = LayerHelper('linear_chain_crf', **locals()) + size = input.shape[1] + transition = helper.create_parameter( + attr=helper.param_attr, + shape=[size + 2, size], + dtype=helper.input_dtype()) + alpha = helper.create_tmp_variable(dtype=helper.input_dtype()) + emission_exps = helper.create_tmp_variable(dtype=helper.input_dtype()) + transition_exps = helper.create_tmp_variable(dtype=helper.input_dtype()) + log_likelihood = helper.create_tmp_variable(dtype=helper.input_dtype()) + helper.append_op( + type='linear_chain_crf', + inputs={"Emission": [input], + "Transition": transition, + "Label": label}, + outputs={ + "Alpha": [alpha], + "EmissionExps": [emission_exps], + "TransitionExps": transition_exps, + "LogLikelihood": log_likelihood + }) + + return log_likelihood + + +def crf_decoding(input, + param_attr, + label=None, + main_program=None, + startup_program=None): + helper = LayerHelper('crf_decoding', **locals()) + transition = helper.get_parameter(param_attr.name) + viterbi_path = helper.create_tmp_variable(dtype=helper.input_dtype()) + helper.append_op( + type='crf_decoding', + inputs={"Emission": [input], + "Transition": transition, + "Label": label}, + outputs={"ViterbiPath": [viterbi_path]}) + + return viterbi_path + + +def cos_sim(X, Y, **kwargs): + """ + This function performs the cosine similarity between two tensors + X and Y and returns that as the output. + """ + helper = LayerHelper('cos_sim', **kwargs) + out = helper.create_tmp_variable(dtype=X.dtype) + xnorm = helper.create_tmp_variable(dtype=X.dtype) + ynorm = helper.create_tmp_variable(dtype=X.dtype) + helper.append_op( + type='cos_sim', + inputs={'X': [X], + 'Y': [Y]}, + outputs={'Out': [out], + 'XNorm': [xnorm], + 'YNorm': [ynorm]}) + return out + + +def cross_entropy(input, label, **kwargs): + """ + This function computes cross_entropy using the input and label. + """ + helper = LayerHelper('cross_entropy', **kwargs) + out = helper.create_tmp_variable(dtype=input.dtype) + helper.append_op( + type='cross_entropy', + inputs={'X': [input], + 'Label': [label]}, + outputs={'Y': [out]}, + attrs=kwargs) + return out + + +def square_error_cost(input, label, **kwargs): + """ + This functions returns the squared error cost using the input and label. + The output is appending the op to do the above. + """ + helper = LayerHelper('square_error_cost', **kwargs) + minus_out = helper.create_tmp_variable(dtype=input.dtype) + helper.append_op( + type='elementwise_sub', + inputs={'X': [input], + 'Y': [label]}, + outputs={'Out': [minus_out]}) + + square_out = helper.create_tmp_variable(dtype=input.dtype) + helper.append_op( + type='square', inputs={'X': [minus_out]}, outputs={'Y': [square_out]}) + return square_out + + +def accuracy(input, label, k=1, correct=None, total=None, **kwargs): + """ + This function computes the accuracy using the input and label. + The output is the top_k inputs and their indices. + """ + helper = LayerHelper("accuracy", **kwargs) + topk_out = helper.create_tmp_variable(dtype=input.dtype) + topk_indices = helper.create_tmp_variable(dtype="int64") + helper.append_op( + type="top_k", + inputs={"X": [input]}, + outputs={"Out": [topk_out], + "Indices": [topk_indices]}, + attrs={"k": k}) + acc_out = helper.create_tmp_variable(dtype="float32") + if correct is None: + correct = helper.create_tmp_variable(dtype="int64") + if total is None: + total = helper.create_tmp_variable(dtype="int64") + helper.append_op( + type="accuracy", + inputs={ + "Out": [topk_out], + "Indices": [topk_indices], + "Label": [label] + }, + outputs={ + "Accuracy": [acc_out], + "Correct": [correct], + "Total": [total], + }) + return acc_out + + +def chunk_eval(input, + label, + chunk_scheme, + num_chunk_types, + excluded_chunk_types=None, + **kwargs): + """ + This function computes and outputs the precision, recall and + F1-score of chunk detection. + """ + helper = LayerHelper("chunk_eval", **kwargs) + + # prepare output + precision = helper.create_tmp_variable(dtype="float32") + recall = helper.create_tmp_variable(dtype="float32") + f1_score = helper.create_tmp_variable(dtype="float32") + num_infer_chunks = helper.create_tmp_variable(dtype="int64") + num_label_chunks = helper.create_tmp_variable(dtype="int64") + num_correct_chunks = helper.create_tmp_variable(dtype="int64") + + helper.append_op( + type="chunk_eval", + inputs={"Inference": [input], + "Label": [label]}, + outputs={ + "Precision": [precision], + "Recall": [recall], + "F1-Score": [f1_score], + "NumInferChunks": [num_infer_chunks], + "NumLabelChunks": [num_label_chunks], + "NumCorrectChunks": [num_correct_chunks] + }, + attrs={ + "num_chunk_types": num_chunk_types, + 'chunk_scheme': chunk_scheme, + 'excluded_chunk_types': excluded_chunk_types or [] + }) + return precision, recall, f1_score, num_infer_chunks, num_label_chunks, num_correct_chunks + + +def sequence_conv(input, + num_filters, + filter_size=3, + filter_stride=1, + padding=None, + bias_attr=None, + param_attr=None, + act=None, + main_program=None, + startup_program=None): + """ + This function creates the op for sequence_conv, using the inputs and + other convolutional configurations for the filters and stride as given + in the input parameters to the function. + """ + + # FIXME(dzh) : want to unify the argument of python layer + # function. So we ignore some unecessary attributes. + # such as, padding_trainable, context_start. + + helper = LayerHelper('sequence_conv', **locals()) + dtype = helper.input_dtype() + filter_shape = [filter_size * input.shape[1], num_filters] + filter_param = helper.create_parameter( + attr=helper.param_attr, shape=filter_shape, dtype=dtype) + pre_bias = helper.create_tmp_variable(dtype) + + helper.append_op( + type='sequence_conv', + inputs={ + 'X': [input], + 'Filter': [filter_param], + }, + outputs={"Out": pre_bias}, + attrs={ + 'contextStride': filter_stride, + 'contextStart': -int(filter_size / 2), + 'contextLength': filter_size + }) + pre_act = helper.append_bias_op(pre_bias) + return helper.append_activation(pre_act) + + +def conv2d(input, + num_filters, + filter_size, + stride=None, + padding=None, + groups=None, + param_attr=None, + bias_attr=None, + act=None, + name=None, + main_program=None, + startup_program=None): + """ + This function creates the op for a 2-dimensional Convolution. + This is performed using the parameters of filters(size, dimensionality etc) + , stride and other configurations for a Convolution operation. + This funciton can also append an activation on top of the + conv-2d output, if mentioned in the input parameters. + """ + + if stride is None: + stride = [1, 1] + helper = LayerHelper('conv2d', **locals()) + dtype = helper.input_dtype() + + num_channels = input.shape[1] + if groups is None: + num_filter_channels = num_channels + else: + if num_channels % groups != 0: + raise ValueError("num_channels must be divisible by groups.") + num_filter_channels = num_channels / groups + + if isinstance(filter_size, int): + filter_size = [filter_size, filter_size] + if isinstance(stride, int): + stride = [stride, stride] + if isinstance(padding, int): + padding = [padding, padding] + + input_shape = input.shape + filter_shape = [num_filters, num_filter_channels] + filter_size + + def _get_default_param_initializer(): + std = (2.0 / (filter_size[0]**2 * num_channels))**0.5 + return Normal(0.0, std, 0) + + filter_param = helper.create_parameter( + attr=helper.param_attr, + shape=filter_shape, + dtype=dtype, + default_initializer=_get_default_param_initializer()) + + pre_bias = helper.create_tmp_variable(dtype) + + helper.append_op( + type='conv2d_cudnn', + inputs={ + 'Input': input, + 'Filter': filter_param, + }, + outputs={"Output": pre_bias}, + attrs={'strides': stride, + 'paddings': padding, + 'groups': groups}) + + pre_act = helper.append_bias_op(pre_bias, dim_start=1, dim_end=2) + + return helper.append_activation(pre_act) + + +def sequence_pool(input, pool_type, **kwargs): + """ + This function add the operator for sequence pooling. + This is applied on top of the input using pool_type mentioned + in the parameters. + """ + helper = LayerHelper('sequence_pool', input=input, **kwargs) + dtype = helper.input_dtype() + pool_out = helper.create_tmp_variable(dtype) + max_index = helper.create_tmp_variable(dtype) + + helper.append_op( + type="sequence_pool", + inputs={"X": input}, + outputs={"Out": pool_out, + "MaxIndex": max_index}, + attrs={"pooltype": pool_type.upper()}) + + return pool_out + + +def pool2d(input, + pool_size, + pool_type, + pool_stride=None, + pool_padding=None, + global_pooling=False, + main_program=None, + startup_program=None): + """ + This function adds the operator for pooling in 2 dimensions, using the + pooling configurations mentioned in input parameters. + """ + if pool_padding is None: + pool_padding = [0, 0] + if pool_stride is None: + pool_stride = [1, 1] + if pool_type not in ["max", "avg"]: + raise ValueError( + "Unknown pool_type: '%s'. It can only be 'max' or 'avg'.", + str(pool_type)) + if isinstance(pool_size, int): + pool_size = [pool_size, pool_size] + if isinstance(pool_stride, int): + pool_stride = [pool_stride, pool_stride] + if isinstance(pool_padding, int): + pool_padding = [pool_padding, pool_padding] + + helper = LayerHelper('pool2d', **locals()) + dtype = helper.input_dtype() + pool_out = helper.create_tmp_variable(dtype) + + helper.append_op( + type="pool2d", + inputs={"X": input}, + outputs={"Out": pool_out}, + attrs={ + "pooling_type": pool_type, + "ksize": pool_size, + "global_pooling": global_pooling, + "strides": pool_stride, + "paddings": pool_padding + }) + + return pool_out + + +def batch_norm(input, + act=None, + is_test=False, + momentum=0.9, + epsilon=1e-05, + param_attr=None, + bias_attr=None, + data_layout='NCHW', + main_program=None, + startup_program=None): + """ + This function helps create an operator to implement + the BatchNorm layer using the configurations from the input parameters. + """ + helper = LayerHelper('batch_norm', **locals()) + dtype = helper.input_dtype() + + input_shape = input.shape + if data_layout == 'NCHW': + channel_num = input_shape[1] + else: + if data_layout == 'NHWC': + channel_num = input_shape[-1] + else: + raise ValueError("unsupported data layout:" + data_layout) + + param_shape = [channel_num] + + # create parameter + scale = helper.create_parameter( + attr=helper.param_attr, + shape=param_shape, + dtype=dtype, + default_initializer=Constant(1.0)) + + bias = helper.create_parameter( + attr=helper.param_attr, shape=param_shape, dtype=dtype, is_bias=True) + + mean = helper.create_global_variable( + dtype=input.dtype, shape=param_shape, persistable=True) + helper.set_variable_initializer(var=mean, initializer=Constant(0.0)) + + variance = helper.create_global_variable( + dtype=input.dtype, shape=param_shape, persistable=True) + helper.set_variable_initializer(var=variance, initializer=Constant(1.0)) + + # create output + # mean and mean_out share the same memory + mean_out = mean + # variance and variance out share the same memory + variance_out = variance + saved_mean = helper.create_tmp_variable(dtype) + saved_variance = helper.create_tmp_variable(dtype) + + batch_norm_out = helper.create_tmp_variable(dtype) + + helper.append_op( + type="batch_norm", + inputs={ + "X": input, + "Scale": scale, + "Bias": bias, + "Mean": mean, + "Variance": variance + }, + outputs={ + "Y": batch_norm_out, + "MeanOut": mean_out, + "VarianceOut": variance_out, + "SavedMean": saved_mean, + "SavedVariance": saved_variance + }, + attrs={"momentum": momentum, + "epsilon": epsilon, + "is_test": is_test}) + + return helper.append_activation(batch_norm_out) + + +def beam_search_decode(ids, scores, main_program=None, startup_program=None): + helper = LayerHelper('beam_search_decode', **locals()) + sentence_ids = helper.create_tmp_variable(dtype=ids.dtype) + sentence_scores = helper.create_tmp_variable(dtype=ids.dtype) + + helper.append_op( + type="beam_search_decode", + inputs={"Ids": ids, + "Scores": scores}, + outputs={ + "SentenceIds": sentence_ids, + "SentenceScores": sentence_scores + }) + + return sentence_ids, sentence_scores + + +def conv2d_transpose(input, + num_filters, + output_size=None, + filter_size=None, + padding=None, + stride=None, + param_attr=None, + main_program=None, + startup_program=None): + """ + The transpose of conv2d layer. + + This layer is also known as deconvolution layer. + + Args: + input(Variable): The input image with [N, C, H, W] format. + num_filters(int): The number of filter. It is as same as the output + image channel. + output_size(int|tuple|None): The output image size. If output size is a + tuple, it must contain two integers, (image_H, image_W). This + parameter only works when filter_size is None. + filter_size(int|tuple|None): The filter size. If filter_size is a tuple, + it must contain two integers, (filter_size_H, filter_size_W). + Otherwise, the filter will be a square. None if use output size to + calculate filter_size + padding(int|tuple): The padding size. If padding is a tuple, it must + contain two integers, (padding_H, padding_W). Otherwise, the + padding_H = padding_W = padding. + stride(int|tuple): The stride size. If stride is a tuple, it must + contain two integers, (stride_H, stride_W). Otherwise, the + stride_H = stride_W = stride. + param_attr: Parameter Attribute. + main_program(Program): the main program + startup_program(Program): the startup program + + Returns: + Variable: Output image. + """ + helper = LayerHelper("conv2d_transpose", **locals()) + if not isinstance(input, Variable): + raise TypeError("Input of conv2d_transpose must be Variable") + input_channel = input.shape[1] + + op_attr = dict() + + if isinstance(padding, int): + op_attr['paddings'] = [padding, padding] + elif padding is not None: + op_attr['paddings'] = padding + + if isinstance(stride, int): + op_attr['strides'] = stride + elif stride is not None: + op_attr['strides'] = stride + + if filter_size is None: + if output_size is None: + raise ValueError("output_size must be set when filter_size is None") + if isinstance(output_size, int): + output_size = [output_size, output_size] + + padding = op_attr.get('paddings', [0, 0]) + stride = op_attr.get('strides', [1, 1]) + + h_in = input.shape[2] + w_in = input.shape[3] + filter_size_h = output_size[0] - \ + (h_in - 1) * stride[0] + 2 * padding[0] + filter_size_w = output_size[1] - \ + (w_in - 1) * stride[1] + 2 * padding[1] + filter_size = [filter_size_h, filter_size_w] + elif isinstance(filter_size, int): + filter_size = [filter_size, filter_size] + + filter_shape = [input_channel, num_filters] + filter_size + img_filter = helper.create_parameter( + dtype=input.dtype, shape=filter_shape, attr=helper.param_attr) + + out = helper.create_tmp_variable(dtype=input.dtype) + helper.append_op( + type='conv2d_transpose', + inputs={'Input': [input], + 'Filter': [img_filter]}, + outputs={'Output': out}, + attrs=op_attr) + + return out diff --git a/python/paddle/v2/fluid/layers/ops.py b/python/paddle/v2/fluid/layers/ops.py new file mode 100644 index 0000000000000000000000000000000000000000..fa312ace60390e5fdd9637dccc71ccf8b247ca47 --- /dev/null +++ b/python/paddle/v2/fluid/layers/ops.py @@ -0,0 +1,9 @@ +from ..registry import register_layer +__all__ = [ + 'mean', 'mul', 'dropout', 'reshape', 'sigmoid', 'scale', 'transpose', + 'sigmoid_cross_entropy_with_logits', 'elementwise_add', 'elementwise_div', + 'elementwise_sub', 'elementwise_mul', 'clip', 'abs' +] + +for _OP in set(__all__): + globals()[_OP] = register_layer(_OP) diff --git a/python/paddle/v2/fluid/layers/tensor.py b/python/paddle/v2/fluid/layers/tensor.py new file mode 100644 index 0000000000000000000000000000000000000000..a839ed897d7a9d4b238a8551b2255b87f207caee --- /dev/null +++ b/python/paddle/v2/fluid/layers/tensor.py @@ -0,0 +1,130 @@ +from ..layer_helper import LayerHelper + +__all__ = [ + 'create_tensor', 'cast', 'concat', 'sums', 'assign', + 'fill_constant_batch_size_like', 'fill_constant', 'ones', 'zeros' +] + + +def create_tensor(dtype, name=None, main_program=None, startup_program=None): + helper = LayerHelper("create_tensor", **locals()) + return helper.create_variable(name=helper.name, dtype=dtype) + + +def cast(x, dtype, main_program=None): + """ + This function takes in the input with input_dtype + and casts it to the output_dtype as the output. + """ + helper = LayerHelper('cast', **locals()) + out = helper.create_tmp_variable(dtype=dtype) + helper.append_op( + type='cast', + inputs={'X': [x]}, + outputs={'Out': [out]}, + attrs={'in_dtype': x.dtype, + 'out_dtype': out.dtype}) + return out + + +def concat(input, axis, main_program=None, startup_program=None): + """ + This function concats the input along the axis mentioned + and returns that as the output. + """ + helper = LayerHelper('concat', **locals()) + out = helper.create_tmp_variable(dtype=helper.input_dtype()) + helper.append_op( + type='concat', + inputs={'X': input}, + outputs={'Out': [out]}, + attrs={'axis': axis}) + return out + + +def sums(input, out=None, main_program=None, startup_program=None): + """ + This function takes in the input and performs the sum operation on it + and returns that as the output. + """ + helper = LayerHelper('sum', **locals()) + if out is None: + out = helper.create_tmp_variable(dtype=helper.input_dtype()) + helper.append_op(type='sum', inputs={'X': input}, outputs={'Out': out}) + return out + + +def assign(input, output, main_program=None, startup_program=None): + helper = LayerHelper('assign', **locals()) + helper.append_op( + type='scale', + inputs={'X': [input]}, + outputs={'Out': [output]}, + attrs={'scale': 1.0}) + return output + + +def fill_constant(shape, + dtype, + value, + out=None, + main_program=None, + startup_program=None): + """ + This function creates a tensor , with shape as mentioned in the input and + specified dtype and fills this up with a constant value that + comes in the input. It also sets the stop_gradient to be True. + """ + helper = LayerHelper("fill_constant", **locals()) + if out is None: + out = helper.create_tmp_variable(dtype=dtype) + helper.append_op( + type='fill_constant', + inputs={}, + outputs={'Out': [out]}, + attrs={'shape': shape, + 'dtype': out.dtype, + 'value': float(value)}) + out.stop_gradient = True + return out + + +def fill_constant_batch_size_like(input, + shape, + dtype, + value, + input_dim_idx=0, + output_dim_idx=0, + main_program=None, + startup_program=None): + helper = LayerHelper("fill_constant_batch_size_like", **locals()) + out = helper.create_tmp_variable(dtype=dtype) + helper.append_op( + type='fill_constant_batch_size_like', + inputs={'Input': input}, + outputs={'Out': [out]}, + attrs={ + 'shape': shape, + 'dtype': out.dtype, + 'value': float(value), + 'input_dim_idx': input_dim_idx, + 'output_dim_idx': output_dim_idx + }) + out.stop_gradient = True + return out + + +def ones(shape, dtype, main_program=None): + """ + This function performs the same function as fill_constant() declared above + with the constant value being 1.0. + """ + return fill_constant(value=1.0, **locals()) + + +def zeros(shape, dtype, main_program=None): + """ + This function performs the same function as fill_constant() declared above + with the constant value being 0.0. + """ + return fill_constant(value=0.0, **locals()) diff --git a/python/paddle/v2/fluid/param_attr.py b/python/paddle/v2/fluid/param_attr.py index 86088fdd7ce17b8b7a9688dc838e69b2aa754013..7952a5ea51c00f72664443fb26faa455e89da7be 100644 --- a/python/paddle/v2/fluid/param_attr.py +++ b/python/paddle/v2/fluid/param_attr.py @@ -36,6 +36,8 @@ class ParamAttr(object): def to_attr(arg): if arg is None: return ParamAttr() + elif isinstance(arg, list) or isinstance(arg, tuple): + return [ParamAttr.to_attr(a) for a in arg] elif isinstance(arg, ParamAttr): return arg elif isinstance(arg, str) or isinstance(arg, unicode): diff --git a/python/paddle/v2/fluid/registry.py b/python/paddle/v2/fluid/registry.py new file mode 100644 index 0000000000000000000000000000000000000000..6f5dd365ded628ad49800f0a04f208ec49cca4c5 --- /dev/null +++ b/python/paddle/v2/fluid/registry.py @@ -0,0 +1,186 @@ +import re +import cStringIO +import warnings +import functools +import inspect + +import proto.framework_pb2 as framework_pb2 +from framework import OpProtoHolder, Variable, Program, Operator +from paddle.v2.fluid.layer_helper import LayerHelper, unique_name + +__all__ = ['deprecated', 'register_layer'] + + +def _convert_(name): + """ + Formatting. + + Args: + name: The name/alias + + This function takes in a name and converts it to a standard format of + group1_group2. Where as per the regular expression, group1 can have + alphabets and numbers and group2 has capital alphabets. + + """ + s1 = re.sub('(.)([A-Z][a-z]+)', r'\1_\2', name) + return re.sub('([a-z0-9])([A-Z])', r'\1_\2', s1).lower() + + +def _generate_doc_string_(op_proto): + """ + Generate docstring by OpProto + + Args: + op_proto (framework_pb2.OpProto): a protobuf message typed OpProto + + Returns: + str: the document string + """ + + def _type_to_str_(tp): + return framework_pb2.AttrType.Name(tp) + + if not isinstance(op_proto, framework_pb2.OpProto): + raise TypeError("OpProto should be `framework_pb2.OpProto`") + + buf = cStringIO.StringIO() + buf.write(op_proto.comment) + buf.write('\nArgs:\n') + for each_input in op_proto.inputs: + line_begin = ' {0}: '.format(_convert_(each_input.name)) + buf.write(line_begin) + buf.write(each_input.comment) + buf.write('\n') + buf.write(' ' * len(line_begin)) + buf.write('Duplicable: ') + buf.write(str(each_input.duplicable)) + buf.write(' Optional: ') + buf.write(str(each_input.dispensable)) + buf.write('\n') + + for each_attr in op_proto.attrs: + buf.write(' ') + buf.write(each_attr.name) + buf.write(' (') + buf.write(_type_to_str_(each_attr.type)) + buf.write('): ') + buf.write(each_attr.comment) + buf.write('\n') + + if len(op_proto.outputs) != 0: + buf.write('\nReturns:\n') + buf.write(' ') + for each_opt in op_proto.outputs: + if not each_opt.intermediate: + break + buf.write(each_opt.comment) + + return buf.getvalue() + + +def register_layer(op_type): + """ + Register an Python layer for an Operator + + Args: + op_type: The name of the operator to be created + + This function takes in the operator type (sigmoid, mean , average etc) and + creates the operator functionality. + + """ + op_proto = OpProtoHolder.instance().get_op_proto(op_type) + not_intermediate_outputs = \ + filter(lambda output: not output.intermediate, op_proto.outputs) + intermediate_outputs = \ + filter(lambda output: output.intermediate, op_proto.outputs) + + if len(not_intermediate_outputs) != 1: + raise ValueError("Only one non intermediate output operator can be", + "automatically generated") + + if not_intermediate_outputs[0].duplicable: + raise ValueError( + "Only non duplicable op can be automatically generated") + + for output in intermediate_outputs: + if output.duplicable: + raise ValueError("The op can be automatically generated only when ", + "all intermediate ops are not duplicable") + + o_name = not_intermediate_outputs[0].name + intermediate_output_names = [output.name for output in intermediate_outputs] + + def infer_and_check_dtype(op_proto, **kwargs): + """ + This function performs the sanity check for dtype and + instance type. + """ + dtype = None + for ipt in op_proto.inputs: + name = _convert_(ipt.name) + val = kwargs.pop(name, []) + if not isinstance(val, list) and not isinstance(val, tuple): + val = [val] + for each in val: + if not isinstance(each, Variable): + raise ValueError("input of {0} must be variable".format( + op_type)) + + if dtype is None: + dtype = each.dtype + elif dtype != each.dtype: + raise ValueError( + "operator {0} must input same dtype. {1} vs {2}".format( + op_type, dtype, each.dtype)) + + return dtype + + def func(**kwargs): + helper = LayerHelper(op_type, **kwargs) + + dtype = infer_and_check_dtype(op_proto, **kwargs) + + inputs = dict() + for ipt in op_proto.inputs: + name = _convert_(ipt.name) + val = kwargs.pop(name, []) + if not isinstance(val, list) and not isinstance(val, tuple): + val = [val] + inputs[ipt.name] = val + + outputs = dict() + out = helper.create_tmp_variable(dtype=dtype) + outputs[o_name] = [out] + for name in intermediate_output_names: + outputs[name] = [helper.create_tmp_variable(dtype=dtype)] + helper.append_op( + type=op_type, inputs=inputs, outputs=outputs, attrs=kwargs) + return helper.append_activation(out) + + func.__name__ = op_type + func.__doc__ = _generate_doc_string_(op_proto) + return func + + +def deprecated(func_or_class): + """ + Deprecated warning decorator. It will result a warning message. + Should be used before class or function, member function + """ + + @functools.wraps(func) + def func_wrapper(*args, **kwargs): + """ + Wrap func with deprecated warning + """ + warnings.simplefilter('always', DeprecationWarning) #turn off filter + warnings.warn( + "Call to deprecated function {}.".format(func.__name__), + category=DeprecationWarning, + stacklevel=2) + warnings.simplefilter('default', DeprecationWarning) #reset filter + return func(*args, **kwargs) + + return func_wrapper diff --git a/python/paddle/v2/fluid/tests/book/test_image_classification_train.py b/python/paddle/v2/fluid/tests/book/test_image_classification_train.py index 4e71b6f345ea7a1e6d29bc4ad810bc5b5f99d456..3d336ffe9582ddd9a2031e7aa7e2c26a772820f8 100644 --- a/python/paddle/v2/fluid/tests/book/test_image_classification_train.py +++ b/python/paddle/v2/fluid/tests/book/test_image_classification_train.py @@ -1,9 +1,9 @@ from __future__ import print_function -import numpy as np +import sys + import paddle.v2 as paddle import paddle.v2.fluid as fluid -import sys def resnet_cifar10(input, depth=32): diff --git a/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py b/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py index d2693b602ea5de9d2d60fbe114820b25119bfa3f..c3591a613acafb268a5bd70618cd4555450bac29 100644 --- a/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py +++ b/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py @@ -150,7 +150,7 @@ def main(): crf_decode = fluid.layers.crf_decoding( input=feature_out, param_attr=fluid.ParamAttr(name='crfw')) - precision, recall, f1_score = fluid.layers.chunk_eval( + chunk_evaluator = fluid.evaluator.ChunkEvaluator( input=crf_decode, label=target, chunk_scheme="IOB", @@ -176,20 +176,21 @@ def main(): batch_id = 0 for pass_id in xrange(PASS_NUM): + chunk_evaluator.reset(exe) for data in train_data(): - outs = exe.run(fluid.default_main_program(), - feed=feeder.feed(data), - fetch_list=[avg_cost, precision, recall, f1_score]) - avg_cost_val = np.array(outs[0]) - precision_val = np.array(outs[1]) - recall_val = np.array(outs[2]) - f1_score_val = np.array(outs[3]) + cost, precision, recall, f1_score = exe.run( + fluid.default_main_program(), + feed=feeder.feed(data), + fetch_list=[avg_cost] + chunk_evaluator.metrics) + pass_precision, pass_recall, pass_f1_score = chunk_evaluator.eval( + exe) if batch_id % 10 == 0: - print("avg_cost=" + str(avg_cost_val)) - print("precision_val=" + str(precision_val)) - print("recall_val:" + str(recall_val)) - print("f1_score_val:" + str(f1_score_val)) + print("avg_cost:" + str(cost) + " precision:" + str( + precision) + " recall:" + str(recall) + " f1_score:" + str( + f1_score) + " pass_precision:" + str( + pass_precision) + " pass_recall:" + str(pass_recall) + + " pass_f1_score:" + str(pass_f1_score)) # exit early for CI exit(0) diff --git a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py index 80f859967979ec07536d652d4ea620fd4ddb2daa..c0b051f862f245b020a872b0a32fa4b560d1d574 100644 --- a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py +++ b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py @@ -1,6 +1,51 @@ import numpy as np import paddle.v2 as paddle import paddle.v2.fluid as fluid +from paddle.v2.fluid.layer_helper import LayerHelper + + +def lstm(x, + c_pre_init, + hidden_dim, + forget_bias=None, + main_program=None, + startup_program=None): + """ + This function helps create an operator for the LSTM (Long Short Term + Memory) cell that can be used inside an RNN. + """ + helper = LayerHelper('lstm_unit', **locals()) + rnn = fluid.layers.StaticRNN() + with rnn.step(): + c_pre = rnn.memory(init=c_pre_init) + x_t = rnn.step_input(x) + + before_fc = fluid.layers.concat( + input=[x_t, c_pre], + axis=1, + main_program=main_program, + startup_program=startup_program) + after_fc = fluid.layers.fc(input=before_fc, + size=hidden_dim * 4, + main_program=main_program, + startup_program=startup_program) + + dtype = x.dtype + c = helper.create_tmp_variable(dtype) + h = helper.create_tmp_variable(dtype) + + helper.append_op( + type='lstm_unit', + inputs={"X": after_fc, + "C_prev": c_pre}, + outputs={"C": c, + "H": h}, + attrs={"forget_bias": forget_bias}) + + rnn.update_memory(c_pre, c) + rnn.output(h) + + return rnn() def lstm_net(dict_dim, class_dim=2, emb_dim=32, seq_len=80, batch_size=50): @@ -23,8 +68,7 @@ def lstm_net(dict_dim, class_dim=2, emb_dim=32, seq_len=80, batch_size=50): c_pre_init = fluid.layers.fill_constant( dtype=emb.dtype, shape=[batch_size, emb_dim], value=0.0) c_pre_init.stop_gradient = False - layer_1_out = fluid.layers.lstm( - emb, c_pre_init=c_pre_init, hidden_dim=emb_dim) + layer_1_out = lstm(emb, c_pre_init=c_pre_init, hidden_dim=emb_dim) layer_1_out = fluid.layers.transpose(x=layer_1_out, axis=[1, 0, 2]) prediction = fluid.layers.fc(input=layer_1_out, diff --git a/python/paddle/v2/fluid/tests/test_chunk_eval_op.py b/python/paddle/v2/fluid/tests/test_chunk_eval_op.py index 819e65a653437f0c34e14403f76317ff3b7f37f4..53bf6f815b8c7baf4c92d9fd488b69722ab0bef5 100644 --- a/python/paddle/v2/fluid/tests/test_chunk_eval_op.py +++ b/python/paddle/v2/fluid/tests/test_chunk_eval_op.py @@ -147,7 +147,13 @@ class TestChunkEvalOp(OpTest): 'Recall': np.asarray( [recall], dtype='float32'), 'F1-Score': np.asarray( - [f1], dtype='float32') + [f1], dtype='float32'), + 'NumInferChunks': np.asarray( + [self.num_infer_chunks], dtype='int64'), + 'NumLabelChunks': np.asarray( + [self.num_label_chunks], dtype='int64'), + 'NumCorrectChunks': np.asarray( + [self.num_correct_chunks], dtype='int64') } def setUp(self): diff --git a/python/paddle/v2/fluid/tests/test_layers.py b/python/paddle/v2/fluid/tests/test_layers.py index 57f6a362defa6efbb168f5959c4c391f3b4b7bbe..9b88080158139f267e253c598e60a4d92a0eff68 100644 --- a/python/paddle/v2/fluid/tests/test_layers.py +++ b/python/paddle/v2/fluid/tests/test_layers.py @@ -29,7 +29,10 @@ class TestBook(unittest.TestCase): label = layers.data(name='label', shape=[1], dtype='int32') hidden1 = layers.fc(input=images, size=128, act='relu') hidden2 = layers.fc(input=hidden1, size=64, act='relu') - predict = layers.fc(input=hidden2, size=10, act='softmax') + predict = layers.fc(input=[hidden2, hidden1], + size=10, + act='softmax', + param_attr=["sftmax.w1", "sftmax.w2"]) cost = layers.cross_entropy(input=predict, label=label) avg_cost = layers.mean(x=cost) self.assertIsNotNone(avg_cost) diff --git a/python/paddle/v2/fluid/tests/test_reduce_op.py b/python/paddle/v2/fluid/tests/test_reduce_op.py index 70359d60cbe656150877673c63e81eae92d8ab9a..a021d4dd91bb9cc1e5d85411b3813b966ef5b296 100644 --- a/python/paddle/v2/fluid/tests/test_reduce_op.py +++ b/python/paddle/v2/fluid/tests/test_reduce_op.py @@ -85,5 +85,19 @@ class Test1DReduce(OpTest): self.check_grad(['X'], 'Out') +class TestReduceAll(OpTest): + def setUp(self): + self.op_type = "reduce_sum" + self.inputs = {'X': np.random.random((5, 6, 2, 10)).astype("float32")} + self.attrs = {'reduce_all': True} + self.outputs = {'Out': self.inputs['X'].sum()} + + def test_check_output(self): + self.check_output() + + def test_check_grad(self): + self.check_grad(['X'], 'Out') + + if __name__ == '__main__': unittest.main() diff --git a/python/paddle/v2/fluid/tests/test_registry.py b/python/paddle/v2/fluid/tests/test_registry.py new file mode 100644 index 0000000000000000000000000000000000000000..f8328f31cf8203f5ea8af2c14417879616ccab71 --- /dev/null +++ b/python/paddle/v2/fluid/tests/test_registry.py @@ -0,0 +1,22 @@ +import unittest +import warnings + +import paddle.v2.fluid as fluid +import paddle.v2.fluid.framework as framework +import paddle.v2.fluid.layers as layers +import paddle.v2.fluid.registry as registry + + +class TestRegistry(unittest.TestCase): + def test_registry_layer(self): + self.layer_type = "mean" + program = framework.Program() + + x = fluid.layers.data(name='X', shape=[10, 10], dtype='float32') + output = layers.mean(x) + place = fluid.CPUPlace() + exe = fluid.Executor(place) + + X = np.random.random((10, 10)).astype("float32") + mean_out = exe.run(program, feed={"X": X}, fetch_list=[output]) + self.assertAlmostEqual(np.mean(X), mean_out) diff --git a/python/paddle/v2/parameters.py b/python/paddle/v2/parameters.py index bd97dc1199fedc8ac91c1c6086957e8cce88bdc4..7b7d1a1d1672802e0e91a857100604758683224e 100644 --- a/python/paddle/v2/parameters.py +++ b/python/paddle/v2/parameters.py @@ -383,19 +383,22 @@ class Parameters(object): params.deserialize(param_name, f) return params - def init_from_tar(self, f): + def init_from_tar(self, f, exclude_params=[]): """ Different from `from_tar`, this interface can be used to init partial network parameters from another saved model. :param f: the initialized model file. :type f: tar file + :param exclude_params: the names of parameters that should + not be initialized from the model file. + :type exclude_params: list of strings :return: Nothing. """ tar_param = Parameters.from_tar(f) for pname in tar_param.names(): - if pname in self.names(): + if pname in self.names() and pname not in exclude_params: self.set(pname, tar_param.get(pname)) diff --git a/python/paddle/v2/reader/decorator.py b/python/paddle/v2/reader/decorator.py index 7e457f987d36e52e9e7c7727b4f996ad31c6bf08..27c82c95f79e0a3e3129627bfa33d85e0d3cd862 100644 --- a/python/paddle/v2/reader/decorator.py +++ b/python/paddle/v2/reader/decorator.py @@ -390,8 +390,6 @@ def pipe_reader(left_cmd, if not callable(parser): raise TypeError("parser must be a callable object") - process = subprocess.Popen( - left_cmd.split(" "), bufsize=bufsize, stdout=subprocess.PIPE) # TODO(typhoonzero): add a thread to read stderr # Always init a decompress object is better than @@ -400,6 +398,8 @@ def pipe_reader(left_cmd, 32 + zlib.MAX_WBITS) # offset 32 to skip the header def reader(): + process = subprocess.Popen( + left_cmd.split(" "), bufsize=bufsize, stdout=subprocess.PIPE) remained = "" while True: buff = process.stdout.read(bufsize) diff --git a/python/paddle/v2/reader/tests/decorator_test.py b/python/paddle/v2/reader/tests/decorator_test.py index 5a92951b100fa51ab6df7039d9c6b54d1f9d963e..06e14796daf27812b9aeb1e4b024f294c7609991 100644 --- a/python/paddle/v2/reader/tests/decorator_test.py +++ b/python/paddle/v2/reader/tests/decorator_test.py @@ -145,5 +145,35 @@ class TestXmap(unittest.TestCase): self.assertEqual(e, mapper(idx)) +class TestPipeReader(unittest.TestCase): + def test_pipe_reader(self): + def simple_parser(lines): + return lines + + import tempfile + + records = [str(i) for i in xrange(5)] + temp = tempfile.NamedTemporaryFile() + try: + with open(temp.name, 'w') as f: + for r in records: + f.write('%s\n' % r) + + cmd = "cat %s" % temp.name + reader = paddle.v2.reader.pipe_reader( + cmd, simple_parser, bufsize=128) + for i in xrange(4): + result = [] + for r in reader(): + result.append(r) + + for idx, e in enumerate(records): + print e, result[idx] + self.assertEqual(e, result[idx]) + finally: + # delete the temporary file + temp.close() + + if __name__ == '__main__': unittest.main() diff --git a/python/setup.py.in b/python/setup.py.in index 9ccb4dc1762ac761212347fa7c7c94b223d75e24..8396fb44cfcee28211b5d3db7684a4adce1fb1f6 100644 --- a/python/setup.py.in +++ b/python/setup.py.in @@ -68,6 +68,7 @@ packages=['paddle', 'paddle.v2.plot', 'paddle.v2.fluid', 'paddle.v2.fluid.proto', + 'paddle.v2.fluid.layers', 'py_paddle'] with open('@PADDLE_SOURCE_DIR@/python/requirements.txt') as f: