diff --git a/docs/conf.py b/docs/conf.py index b47ce9ab2d84733d29cf0341f809ccb0c47d3fbc..34eb3c9de7decaa50c29b142ec22989155d4e838 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -10,9 +10,6 @@ project = u'MiAI Compute Engine' author = u'%s Developers' % project copyright = u'2018, %s' % author -version = u'0.6' -release = u'0.6.0 alpha' - source_parsers = { '.md': recommonmark.parser.CommonMarkParser, } diff --git a/docs/development/adding_a_new_op.md b/docs/development/adding_a_new_op.md index a6f204f2c2eeb9ad60331c0677e3210514551d34..be0c82b3e62d5a6569cbd8dc7a65492a3bacc188 100644 --- a/docs/development/adding_a_new_op.md +++ b/docs/development/adding_a_new_op.md @@ -3,7 +3,7 @@ Adding a new Op You can create a custom op if it is not supported yet. -To add a custom op, you need to finish the following steps. +To add a custom op, you need to finish the following steps: Define the Op class -------------------- @@ -95,3 +95,7 @@ Add test and benchmark ---------------------- It's strongly recommended to add unit test and micro benchmark for your new Op. If you wish to contribute back, it's required. + +Document the new Op +--------------------- +Finally, add an entry in operator table in the document. diff --git a/docs/development/contributing.md b/docs/development/contributing.md index 97671e74c9cfc9f5b1d3183eea67a2c5fd7a24f0..aac0e9f110003543b7083c7f64d6236a69f112a0 100644 --- a/docs/development/contributing.md +++ b/docs/development/contributing.md @@ -34,7 +34,8 @@ clang-format -style="{BasedOnStyle: google, \ C++ logging guideline --------------------- -The rule of VLOG level: +VLOG is used for verbose logging, which is configured by environment variable +`MACE_CPP_MIN_VLOG_LEVEL`. The guideline of VLOG level is as follows: ``` 0. Ad hoc debug logging, should only be added in test or temporary ad hoc diff --git a/docs/development/memory_layout.rst b/docs/development/memory_layout.rst index f8e428ca7a6f59b390a78e3264289778e753ce80..2065e66c541c2416030e0738f6296b23322f9fd0 100644 --- a/docs/development/memory_layout.rst +++ b/docs/development/memory_layout.rst @@ -5,17 +5,21 @@ CPU runtime memory layout ------------------------- The CPU tensor buffer is organized in the following order: -+-----------------------------+--------------+ -| Tensor type | Buffer | -+=============================+==============+ -| Intermediate input/output | NCHW | -+-----------------------------+--------------+ -| Convolution Filter | OIHW | -+-----------------------------+--------------+ -| Depthwise Convolution Filter| MIHW | -+-----------------------------+--------------+ -| 1-D Argument, length = W | W | -+-----------------------------+--------------+ +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Tensor type + - Buffer + * - Intermediate input/output + - NCHW + * - Convolution Filter + - OIHW + * - Depthwise Convolution Filter + - MIHW + * - 1-D Argument, length = W + - W OpenCL runtime memory layout ----------------------------- @@ -34,66 +38,117 @@ Input/Output Tensor The Input/Output Tensor is stored in NHWC format: -+---------------------------+--------+----------------------------+-----------------------------+ -|Tensor type | Buffer | Image size [width, height] | Explanation | -+===========================+========+============================+=============================+ -|Channel-Major Input/Output | NHWC | [W * (C+3)/4, N * H] | Default Input/Output format | -+---------------------------+--------+----------------------------+-----------------------------+ -|Height-Major Input/Output | NHWC | [W * C, N * (H+3)/4] | Winograd Convolution format | -+---------------------------+--------+----------------------------+-----------------------------+ -|Width-Major Input/Output | NHWC | [(W+3)/4 * C, N * H] | Winograd Convolution format | -+---------------------------+--------+----------------------------+-----------------------------+ +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Tensor type + - Buffer + - Image size [width, height] + - Explanation + * - Channel-Major Input/Output + - NHWC + - [W * (C+3)/4, N * H] + - Default Input/Output format + * - Height-Major Input/Output + - NHWC + - [W * C, N * (H+3)/4 + - Winograd Convolution format + * - Width-Major Input/Output + - NHWC + - [(W+3)/4 * C, N * H] + - Winograd Convolution format Each Pixel of **Image** contains 4 elements. The below table list the coordination relation between **Image** and **Buffer**. -+---------------------------+-------------------------------------------------------------------------+-------------+ -|Tensor type | Pixel coordinate relationship | Explanation | -+===========================+=========================================================================+=============+ -|Channel-Major Input/Output | P[i, j] = {E[n, h, w, c] | (n=j/H, h=j%H, w=i%W, c=[i/W * 4 + k])} | k=[0, 4) | -+---------------------------+-------------------------------------------------------------------------+-------------+ -|Height-Major Input/Output | P[i, j] = {E[n, h, w, c] | (n=j%N, h=[j/H*4 + k], w=i%W, c=i/W)} | k=[0, 4) | -+---------------------------+-------------------------------------------------------------------------+-------------+ -|Width-Major Input/Output | P[i, j] = {E[n, h, w, c] | (n=j/H, h=j%H, w=[i%W*4 + k], c=i/W)} | k=[0, 4) | -+---------------------------+-------------------------------------------------------------------------+-------------+ - +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Tensor type + - Pixel coordinate relationship + - Explanation + * - Channel-Major Input/Output + - P[i, j] = {E[n, h, w, c] | (n=j/H, h=j%H, w=i%W, c=[i/W * 4 + k])} + - k=[0, 4) + * - Height-Major Input/Output + - P[i, j] = {E[n, h, w, c] | (n=j%N, h=[j/H*4 + k], w=i%W, c=i/W)} + - k=[0, 4) + * - Width-Major Input/Output + - P[i, j] = {E[n, h, w, c] | (n=j/H, h=j%H, w=[i%W*4 + k], c=i/W)} + - k=[0, 4) Filter Tensor ~~~~~~~~~~~~~ -+----------------------------+------+---------------------------------+------------------------------------------------------------------------------+ -| Tensor |Buffer| Image size [width, height] | Explanation | -+============================+======+=================================+==============================================================================+ -|Convolution Filter | HWOI | [RoundUp<4>(I), H * W * (O+3)/4]|Convolution filter format，There is no difference compared to [H*w*I, (O+3)/4]| -+----------------------------+------+---------------------------------+------------------------------------------------------------------------------+ -|Depthwise Convlution Filter | HWIM | [H * W * M, (I+3)/4] |Depthwise-Convolution filter format | -+----------------------------+------+---------------------------------+------------------------------------------------------------------------------+ +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Tensor + - Buffer + - Image size [width, height] + - Explanation + * - Convolution Filter + - HWOI + - [RoundUp<4>(I), H * W * (O+3)/4] + - Convolution filter format，There is no difference compared to [H*w*I, (O+3)/4] + * - Depthwise Convlution Filter + - HWIM + - [H * W * M, (I+3)/4] + - Depthwise-Convolution filter format Each Pixel of **Image** contains 4 elements. The below table list the coordination relation between **Image** and **Buffer**. -+----------------------------+-------------------------------------------------------------------+---------------------------------------+ -|Tensor type | Pixel coordinate relationship | Explanation | -+============================+===================================================================+=======================================+ -|Convolution Filter | P[m, n] = {E[h, w, o, i] | (h=T/W, w=T%W, o=[n/HW*4+k], i=m)}| HW= H * W, T=n%HW, k=[0, 4) | -+----------------------------+-------------------------------------------------------------------+---------------------------------------+ -|Depthwise Convlution Filter | P[m, n] = {E[h, w, i, 0] | (h=m/W, w=m%W, i=[n*4+k])} | only support multiplier == 1, k=[0, 4)| -+----------------------------+-------------------------------------------------------------------+---------------------------------------+ +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Tensor type + - Pixel coordinate relationship + - Explanation + * - Convolution Filter + - P[m, n] = {E[h, w, o, i] | (h=T/W, w=T%W, o=[n/HW*4+k], i=m)} + - HW= H * W, T=n%HW, k=[0, 4) + * - Depthwise Convlution Filter + - P[m, n] = {E[h, w, i, 0] | (h=m/W, w=m%W, i=[n*4+k])} + - only support multiplier == 1, k=[0, 4) 1-D Argument Tensor ~~~~~~~~~~~~~~~~~~~ -+----------------+----------+------------------------------+---------------------------------+ -| Tensor type | Buffer | Image size [width, height] | Explanation | -+================+==========+==============================+=================================+ -| 1-D Argument | W | [(W+3)/4, 1] | 1D argument format, e.g. Bias | -+----------------+----------+------------------------------+---------------------------------+ +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Tensor type + - Buffer + - Image size [width, height] + - Explanation + * - 1-D Argument + - W + - [(W+3)/4, 1] + - 1D argument format, e.g. Bias Each Pixel of **Image** contains 4 elements. The below table list the coordination relation between **Image** and **Buffer**. -+--------------+---------------------------------+-------------+ -| Tensor type | Pixel coordinate relationship | Explanation | -+==============+=================================+=============+ -|1-D Argument | P[i, 0] = {E[w] | w=i*4+k} | k=[0, 4) | -+--------------+---------------------------------+-------------+ +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Tensor type + - Pixel coordinate relationship + - Explanation + * - 1-D Argument + - P[i, 0] = {E[w] | w=i*4+k} + - k=[0, 4) + diff --git a/docs/faq.md b/docs/faq.md index a96305a5ff4fab48662f77a654d7c3ab6819e3d3..01d1cd9acf12d39526802c714b39c9a922cbcdbf 100644 --- a/docs/faq.md +++ b/docs/faq.md @@ -1,4 +1,4 @@ -Frequently Asked Questions +Frequently asked questions ========================== Why is the generated static library file size so huge? diff --git a/docs/getting_started/create_a_model_deployment.rst b/docs/getting_started/create_a_model_deployment.rst index 15a5b06cc26f893dba421d66ba4d579a46cbce6b..bf47aed5db09d34f4bfb09ac79a519513751999b 100644 --- a/docs/getting_started/create_a_model_deployment.rst +++ b/docs/getting_started/create_a_model_deployment.rst @@ -1,105 +1,68 @@ -Create a model deployment -========================= +Create a model deployment file +============================== -Each YAML deployment script describes a case of deployments (for example, -a smart camera application may contains face recognition, object recognition, -and voice recognition models, which can be defined in one deployment file), -which will generate one static library (if more than one ABIs specified, -there will be one static library for each). Each YAML scripts can contains one -or more models. +The first step to deploy you models is to create a YAML model deployment +file. +One deployment file describes a case of model deployment, +each file will generate one static library (if more than one ABIs specified, +there will be one static library for each). The deployment file can contains +one or more models, for example, a smart camera application may contains face +recognition, object recognition, and voice recognition models, which can be +defined in one deployment file), -Model deployment file example -------------------------------- -TODO: change to a link to a standalone file with comments. -.. code:: yaml +Example +---------- +Here is an deployment file example used by Android demo application. - # 配置文件名会被用作生成库的名称：libmace-${filename}.a - target_abis: [armeabi-v7a, arm64-v8a] - # 具体机型的soc编号，可以使用`adb shell getprop | grep ro.board.platform | cut -d [ -f3 | cut -d ] -f1`获取 - target_socs: [msm8998] - embed_model_data: 1 - vlog_level: 0 - models: # 一个配置文件可以包含多个模型的配置信息，最终生成的库中包含多个模型 - first_net: # 模型的标签，在调度模型的时候，会用这个变量 - platform: tensorflow - model_file_path: path/to/model64.pb # also support http:// and https:// - model_sha256_checksum: 7f7462333406e7dea87222737590ebb7d94490194d2f21a7d72bafa87e64e9f9 - input_nodes: input_node - output_nodes: output_node - input_shapes: 1,64,64,3 - output_shapes: 1,64,64,2 - runtime: gpu - limit_opencl_kernel_time: 0 - dsp_mode: 0 - obfuscate: 1 - fast_conv: 0 - input_files: - - path/to/input_files # support http:// - second_net: - platform: caffe - model_file_path: path/to/model.prototxt - weight_file_path: path/to/weight.caffemodel - model_sha256_checksum: 05d92625809dc9edd6484882335c48c043397aed450a168d75eb8b538e86881a - weight_sha256_checksum: 05d92625809dc9edd6484882335c48c043397aed450a168d75eb8b538e86881a - input_nodes: - - input_node0 - - input_node1 - output_nodes: - - output_node0 - - output_node1 - input_shapes: - - 1,256,256,3 - - 1,128,128,3 - output_shapes: - - 1,256,256,2 - - 1,1,1,2 - runtime: cpu - limit_opencl_kernel_time: 1 - dsp_mode: 0 - obfuscate: 1 - fast_conv: 0 - input_files: - - path/to/input_files # support http:// +TODO: change this example file to the demo deployment file +(reuse the same file) and rename to a reasonable name. + +.. literalinclude:: models/demo_app_models.yaml + :language: yaml Configurations -------------------- -+--------------------------+----------------------------------------------------------------------------------------+ -| Configuration key | Description | -+==========================+========================================================================================+ -| target_abis | The target ABI to build, can be one or more of 'host', 'armeabi-v7a' or 'arm64-v8a' | -+--------------------------+----------------------------------------------------------------------------------------+ -| embed_model_data | Whether embedding model weights as the code, default to 1 | -+--------------------------+----------------------------------------------------------------------------------------+ -| platform | The source framework, tensorflow or caffe | -+--------------------------+----------------------------------------------------------------------------------------+ -| model_file_path | The path of the model file, can be local or remote | -+--------------------------+----------------------------------------------------------------------------------------+ -| weight_file_path | The path of the model weights file, used by Caffe model | -+--------------------------+----------------------------------------------------------------------------------------+ -| model_sha256_checksum | The SHA256 checksum of the model file | -+--------------------------+----------------------------------------------------------------------------------------+ -| weight_sha256_checksum | The SHA256 checksum of the weight file, used by Caffe model | -+--------------------------+----------------------------------------------------------------------------------------+ -| input_nodes | The input node names, one or more strings | -+--------------------------+----------------------------------------------------------------------------------------+ -| output_nodes | The output node names, one or more strings | -+--------------------------+----------------------------------------------------------------------------------------+ -| input_shapes | The shapes of the input nodes, in NHWC order | -+--------------------------+----------------------------------------------------------------------------------------+ -| output_shapes | The shapes of the output nodes, in NHWC order | -+--------------------------+----------------------------------------------------------------------------------------+ -| runtime | The running device, one of CPU, GPU or DSP | -+--------------------------+----------------------------------------------------------------------------------------+ -| limit_opencl_kernel_time | Whether splitting the OpenCL kernel within 1 ms to keep UI responsiveness, default to 0| -+--------------------------+----------------------------------------------------------------------------------------+ -| dsp_mode | Control the DSP precision and performance, default to 0 usually works for most cases | -+--------------------------+----------------------------------------------------------------------------------------+ -| obfuscate | Whether to obfuscate the model operator name, default to 0 | -+--------------------------+----------------------------------------------------------------------------------------+ -| fast_conv | Whether to enable Winograd convolution, **will increase memory consumption** | -+--------------------------+----------------------------------------------------------------------------------------+ -| input_files | Specify Numpy validation inputs. When not provided, [-1, 1] random values will be used | -+--------------------------+----------------------------------------------------------------------------------------+ +.. list-table:: + :widths: auto + :header-rows: 1 + :align: left + + * - Configuration key + - Description + * - target_abis + - The target ABI to build, can be one or more of 'host', 'armeabi-v7a' or 'arm64-v8a' + * - embed_model_data + - Whether embedding model weights as the code, default to 1 + * - platform + - The source framework, tensorflow or caffe + * - model_file_path + - The path of the model file, can be local or remote + * - weight_file_path + - The path of the model weights file, used by Caffe model + * - model_sha256_checksum + - The SHA256 checksum of the model file + * - weight_sha256_checksum + - The SHA256 checksum of the weight file, used by Caffe model + * - input_nodes + - The input node names, one or more strings + * - output_nodes + - The output node names, one or more strings + * - input_shapes + - The shapes of the input nodes, in NHWC order + * - output_shapes + - The shapes of the output nodes, in NHWC order + * - runtime + - The running device, one of CPU, GPU or DSP + * - limit_opencl_kernel_time + - Whether splitting the OpenCL kernel within 1 ms to keep UI responsiveness, default to 0 + * - dsp_mode + - Control the DSP precision and performance, default to 0 usually works for most cases + * - obfuscate + - Whether to obfuscate the model operator name, default to 0 + * - fast_conv + - Whether to enable Winograd convolution, **will increase memory consumption** + * - input_files + - Specify Numpy validation inputs. When not provided, [-1, 1] random values will be used diff --git a/docs/getting_started/docker.md b/docs/getting_started/docker.md new file mode 100644 index 0000000000000000000000000000000000000000..f58f4a64f7320552849a543fca23ab20ea71b5e1 --- /dev/null +++ b/docs/getting_started/docker.md @@ -0,0 +1,27 @@ +Docker Images +============= + +* Login in [Xiaomi Docker Registry](http://docs.api.xiaomi.net/docker-registry/) + +``` +docker login cr.d.xiaomi.net +``` + +* Build with `Dockerfile` + +``` +docker build -t cr.d.xiaomi.net/mace/mace-dev +``` + +* Pull image from docker registry + +``` +docker pull cr.d.xiaomi.net/mace/mace-dev +``` + +* Create container + +``` +# Set 'host' network to use ADB +docker run -it --rm -v /local/path:/container/path --net=host cr.d.xiaomi.net/mace/mace-dev /bin/bash +``` diff --git a/docs/getting_started/docker.rst b/docs/getting_started/docker.rst deleted file mode 100644 index 3c6f5ec0e8701ef786ebed6fe97ffd7fedc31e82..0000000000000000000000000000000000000000 --- a/docs/getting_started/docker.rst +++ /dev/null @@ -1,19 +0,0 @@ -Docker Images -============= - -- Login in `Xiaomi Docker - Registry `__ - -``docker login cr.d.xiaomi.net`` - -- Build with ``Dockerfile`` - -``docker build -t cr.d.xiaomi.net/mace/mace-dev .`` - -- Pull image from docker registry - -``docker pull cr.d.xiaomi.net/mace/mace-dev`` - -- Create container - -``# Set 'host' network to use ADB docker run -it --rm -v /local/path:/container/path --net=host cr.d.xiaomi.net/mace/mace-dev /bin/bash`` diff --git a/docs/getting_started/models/demo_app_models.yaml b/docs/getting_started/models/demo_app_models.yaml new file mode 100644 index 0000000000000000000000000000000000000000..878f83156bcd6dfe5f8fbe55710580ee3bca02e2 --- /dev/null +++ b/docs/getting_started/models/demo_app_models.yaml @@ -0,0 +1,46 @@ +# 配置文件名会被用作生成库的名称：libmace-${filename}.a +target_abis: [armeabi-v7a, arm64-v8a] +# 具体机型的soc编号，可以使用`adb shell getprop | grep ro.board.platform | cut -d [ -f3 | cut -d ] -f1`获取 +target_socs: [msm8998] +embed_model_data: 1 +models: # 一个配置文件可以包含多个模型的配置信息，最终生成的库中包含多个模型 + first_net: # 模型的标签，在调度模型的时候，会用这个变量 + platform: tensorflow + model_file_path: path/to/model64.pb # also support http:// and https:// + model_sha256_checksum: 7f7462333406e7dea87222737590ebb7d94490194d2f21a7d72bafa87e64e9f9 + input_nodes: input_node + output_nodes: output_node + input_shapes: 1,64,64,3 + output_shapes: 1,64,64,2 + runtime: gpu + limit_opencl_kernel_time: 0 + dsp_mode: 0 + obfuscate: 1 + fast_conv: 0 + input_files: + - path/to/input_files # support http:// + second_net: + platform: caffe + model_file_path: path/to/model.prototxt + weight_file_path: path/to/weight.caffemodel + model_sha256_checksum: 05d92625809dc9edd6484882335c48c043397aed450a168d75eb8b538e86881a + weight_sha256_checksum: 05d92625809dc9edd6484882335c48c043397aed450a168d75eb8b538e86881a + input_nodes: + - input_node0 + - input_node1 + output_nodes: + - output_node0 + - output_node1 + input_shapes: + - 1,256,256,3 + - 1,128,128,3 + output_shapes: + - 1,256,256,2 + - 1,1,1,2 + runtime: cpu + limit_opencl_kernel_time: 1 + dsp_mode: 0 + obfuscate: 1 + fast_conv: 0 + input_files: + - path/to/input_files # support http:// diff --git a/docs/getting_started/op_lists.rst b/docs/getting_started/op_lists.rst index 6afa5d0622494f2e2db7ce67196a2982c293b4a0..803d32170fb6eaa6a2b742a376158b00bab2ea7c 100644 --- a/docs/getting_started/op_lists.rst +++ b/docs/getting_started/op_lists.rst @@ -1,82 +1,46 @@ Operator lists ============== -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| Operator | Android NN | Status | Remark | -+==================================+==============+========+=======================================================+ -| ADD | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| AVERAGE\_POOL\_2D | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| BATCH\_NORM | | Y | Fusion with activation is supported | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| BIAS\_ADD | | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| CHANNEL\_SHUFFLE | | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| CONCATENATION | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| CONV\_2D | Y | Y | Fusion with BN and activation layer is supported | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| DEPTHWISE\_CONV\_2D | Y | Y | Only multiplier = 1 is supported; Fusion is supported | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| DEPTH\_TO\_SPACE | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| DEQUANTIZE | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| EMBEDDING\_LOOKUP | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| FLOOR | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| FULLY\_CONNECTED | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| GROUP\_CONV\_2D | | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| HASHTABLE\_LOOKUP | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| L2\_NORMALIZATION | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| L2\_POOL\_2D | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| LOCAL\_RESPONSE\_NORMALIZATION | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| LOGISTIC | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| LSH\_PROJECTION | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| LSTM | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| MATMUL | | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| MAX\_POOL\_2D | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| MUL | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| PSROI\_ALIGN | | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| PRELU | | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RELU | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RELU1 | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RELU6 | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RELUX | | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RESHAPE | Y | Y | Limited support | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RESIZE\_BILINEAR | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RNN | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| RPN\_PROPOSAL\_LAYER | | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| SOFTMAX | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| SPACE\_TO\_DEPTH | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| SVDF | Y | | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ -| TANH | Y | Y | | -+----------------------------------+--------------+--------+-------------------------------------------------------+ +.. Please keep in chronological order when editing +.. csv-table:: + :widths: auto + :header: "Operator","Android NN","Supported","Remark" + + "ADD","Y","Y","" + "AVERAGE_POOL_2D","Y","Y","" + "BATCH_NORM","","Y","Fusion with activation is supported" + "BIAS_ADD","","Y","" + "CHANNEL_SHUFFLE","","Y","" + "CONCATENATION","Y","Y","" + "CONV_2D","Y","Y","Fusion with BN and activation layer is supported" + "DEPTHWISE_CONV_2D","Y","Y","Only multiplier = 1 is supported; Fusion is supported" + "DEPTH_TO_SPACE","Y","Y","" + "DEQUANTIZE","Y","","" + "EMBEDDING_LOOKUP","Y","","" + "FLOOR","Y","","" + "FULLY_CONNECTED","Y","Y","" + "GROUP_CONV_2D","","","" + "HASHTABLE_LOOKUP","Y","","" + "L2_NORMALIZATION","Y","","" + "L2_POOL_2D","Y","","" + "LOCAL_RESPONSE_NORMALIZATION","Y","Y","" + "LOGISTIC","Y","Y","" + "LSH_PROJECTION","Y","","" + "LSTM","Y","","" + "MATMUL","","Y","" + "MAX_POOL_2D","Y","Y","" + "MUL","Y","","" + "PSROI_ALIGN","","Y","" + "PRELU","","Y","" + "RELU","Y","Y","" + "RELU1","Y","Y","" + "RELU6","Y","Y","" + "RELUX","","Y","" + "RESHAPE","Y","Y","Limited support" + "RESIZE_BILINEAR","Y","Y","" + "RNN","Y","","" + "RPN_PROPOSAL_LAYER","","Y","" + "SOFTMAX","Y","Y","" + "SPACE_TO_DEPTH","Y","Y","" + "SVDF","Y","","" + "TANH","Y","Y","" diff --git a/docs/index.rst b/docs/index.rst index 08400726ed711386585ec0acf953404562ae9af0..70cfab0fdd9f1c69a62108dd0773f9dbadb21d37 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -11,8 +11,8 @@ The main documentation is organized into the following sections: getting_started/introduction getting_started/create_a_model_deployment - getting_started/how_to_build getting_started/docker + getting_started/how_to_build getting_started/op_lists .. toctree::