Merge pull request #86 from SunAhong1993/develop

add directly map op and custom layer readme

add_caffe_custom_layer.md

+## 如何转换Caffe自定义Layer
+
+本文档介绍如何将Caffe自定义Layer转换为PaddlePaddle模型中的对应实现, 用户可根据自己需要，添加代码实现自定义层，从而支持模型的完整转换。            
+***步骤一 下载代码***        
+此处涉及修改源码，应先卸载x2paddle，并且下载源码，主要有以下两步完成：
+```
+pip uninstall x2paddle
+pip install git+https://github.com/PaddlePaddle/X2Paddle.git@develop
+```
+
+***步骤二 编译caffe.proto***   
+该步骤依赖protobuf编译器，其安装过程有以下两种方式：
+> 选择一：pip install protobuf             
+> 选择二：使用[官方源码](https://github.com/protocolbuffers/protobuf)进行编译
+
+使用脚本./tools/compile.sh将caffe.proto（包含所需的自定义Layer信息）编译成我们所需的目标语言（Python）         
+使用方式：
+```
+bash ./toos/compile.sh /home/root/caffe/src/caffe/proto
+# /home/root/caffe/src/caffe/proto为caffe.proto的存放路径，生成的caffe_pb2.py也将保存在该路径下
+```
+
+***步骤三 添加自定义Layer的实现代码***
+- 进入./x2paddle/op_mapper/caffe_custom_layer，创建.py文件，例如mylayer.py
+- 仿照./x2paddle/op_mapper/caffe_custom_layer中的其他文件，在mylayer.py中主要需要实现3个函数，下面以roipooling.py为例分析代码：
+  1. `def roipooling_shape(input_shape, pooled_w=None, pooled_h=None)`  
+     参数：
+     1. input_shape（list）：其中每个元素代表该层每个输入数据的shape，为必须传入的参数   
+     2. pooled_w（int）：代表ROI Pooling的kernel的宽，其命名与.prototxt中roi_pooling_param中的key一致
+     3. pooled_h（int）：代表ROI Pooling的kernel的高，其命名与.prototxt中roi_pooling_param中的key一致          
+
+     功能：计算出进行ROI Pooling后的shape         
+     返回：一个list，其中每个元素代表每个输出数据的shape，由于ROI Pooling的输出数据只有一个，所以其list长度为1     
+
+  2. `def roipooling_layer(inputs, input_shape=None, name=None, pooled_w=None, pooled_h=None, spatial_scale=None)` 
+
+     参数：
+     1. inputs（list）：其中每个元素代表该层每个输入数据，为必须传入的参数
+     2. input_shape（list）：其中每个元素代表该层每个输入数据的shape，为必须传入的参数  
+     3. name（str）：ROI Pooling层的名字，为必须传入的参数  
+     4. pooled_w（int）：代表ROI Pooling的kernel的宽，其命名与.prototxt中roi_pooling_param中的key一致
+     5. pooled_h（int）：代表ROI Pooling的kernel的高，其命名与.prototxt中roi_pooling_param中的key一致
+     6. spatial_scale（float）：用于将ROI坐标从输入比例转换为池化时使用的比例，其命名与.prototxt中roi_pooling_param中的key一致            
+
+     功能：运用PaddlePaddle完成组网来实现`roipooling_layer`的功能         
+     返回：一个Variable，为组网后的结果
+
+  3. `def roipooling_weights(name, data=None)`  
+
+     参数：
+     1. name（str）：ROI Pooling层的名字，为必须传入的参数
+     2. data（list）：由Caffe模型.caffemodel获得的关于roipooling的参数，roipooling的参数为None
+
+     功能：为每个参数（例如kernel、bias等）命名；同时，若Caffe中该层参数与PaddlePaddle中参数的格式不一致，则变换操作也在该函数中实现。     
+     返回：一个list，包含每个参数的名字。
+
+- 在roipooling.py中注册`roipooling`，主要运用下述代码实现：
+  ```
+  register(kind='ROIPooling', shape=roipooling_shape, layer=roipooling_layer, weights=roipooling_weights)
+  # kind为在model.prototxt中roipooling的type
+  ```
+- 在./x2paddle/op_mapper/caffe_custom_layer/\_\_init\_\_.py中引入该层的使用
+  ```
+  from . import roipooling
+  ```
+
+
+***步骤四 运行转换代码***
+```
+# 在X2Paddle目录下安装x2paddle
+python setup.py install
+# 运行转换代码
+x2paddle --framework=caffe 
+         --prototxt=deploy.proto 
+         --weight=deploy.caffemodel 
+         --save_dir=pd_model 
+         --caffe_proto=/home/root/caffe/src/caffe/proto/caffe_pb2.py
+```

tools/compile.sh

+#!/bin/bash
+
+#function:
+#   script used to generate caffe_pb2.py from caffe.proto using protoc
+#
+
+PROTOC=`which protoc`
+if [[ -z $PROTOC ]];then
+    echo "not found protoc, you should first install it following this[https://github.com/google/protobuf/releases]"
+    exit 1
+fi
+
+WORK_ROOT=$1
+PY_NAME="$WORK_ROOT/caffe_pb2.py"
+$PROTOC --proto_path=$WORK_ROOT --python_out=$WORK_ROOT $WORK_ROOT/caffe.proto
+ret=$?
+
+if [ -e "$PY_NAME" ];then
+    echo "succeed to generate [$PY_NAME]"
+    exit 0
+else
+    echo "failed to generate [$PY_NAME]"
+fi
+exit $ret

x2paddle/op_mapper/caffe_op_mapper.py

@@ -22,6 +22,13 @@ from x2paddle.op_mapper.caffe_custom_layer import *
 
 
 class CaffeOpMapper(OpMapper):
+    directly_map_ops = {
+        'ReLU': 'relu',
+        'AbsVal': 'abs',
+        'Sigmoid': 'sigmoid',
+        'TanH': 'tanh',
+    }
+
     def __init__(self, decoder):
         super(CaffeOpMapper, self).__init__()
         self.graph = decoder.caffe_graph
@@ -40,8 +47,12 @@ class CaffeOpMapper(OpMapper):
             elif op in custom_layers:
                 self.set_node_shape(node, is_fluid_op=False)
                 self.deal_custom_layer(node)
+            elif op in self.directly_map_ops:
+                self.set_node_shape(node)
+                self.directly_map(node)
             else:
-                raise Exception("Model are not supported yet.")
+                raise Exception(
+                    "The op {} in model is not supported yet.".format(op))
 
     def op_checker(self):
         unsupported_ops = set()
@@ -180,6 +191,22 @@ class CaffeOpMapper(OpMapper):
                                   output=node,
                                   param_attr=attr)
 
+    def MemoryData(self, node):
+        # TODO(syf): Paddlepaddle can't fully support
+        shape = node.output_shape[0][1:]
+        dtype = 'float32'
+        attr = {
+            'dtype': string(dtype),
+            'shape': shape,
+            'name': string(node.layer_name)
+        }
+        node.fluid_code.add_layer("data",
+                                  inputs=None,
+                                  output=node.layer_name + '0',
+                                  param_attr=attr)
+        node.fluid_code.add_note('{} = [{}]'.format(node.layer_name,
+                                                    node.layer_name + '0'))
+
     def Convolution(self, node):
         data = node.data
         assert data is not None, 'The parameter of {} (type is {}) is not set. You need to use python package of caffe to set the default value.'.format(
@@ -290,16 +317,6 @@ class CaffeOpMapper(OpMapper):
                                   output=node,
                                   param_attr=attr)
 
-    def ReLU(self, node):
-        assert len(
-            node.inputs) == 1, 'The count of ReLU node\'s input is not 1.'
-        input = self.graph.get_bottom_node(node, idx=0, copy=True)
-        attr = {'name': string(node.layer_name)}
-        node.fluid_code.add_layer("relu",
-                                  inputs=input,
-                                  output=node,
-                                  param_attr=attr)
-
     def LRN(self, node):
         assert len(node.inputs) == 1, 'The count of LRN node\'s input is not 1.'
         params = node.layer.lrn_param
@@ -445,26 +462,6 @@ class CaffeOpMapper(OpMapper):
                                   output=node,
                                   param_attr=attr)
 
-    def Sigmoid(self, node):
-        assert len(
-            node.inputs) == 1, 'The count of PReLU node\'s input is not 1.'
-        input = self.graph.get_bottom_node(node, idx=0, copy=True)
-        attr = {'name': string(node.layer_name)}
-        node.fluid_code.add_layer("sigmoid",
-                                  inputs=input,
-                                  output=node,
-                                  param_attr=attr)
-
-    def AbsVal(self, node):
-        assert len(
-            node.inputs) == 1, 'The count of PReLU node\'s input is not 1.'
-        input = self.graph.get_bottom_node(node, idx=0, copy=True)
-        attr = {'name': string(node.layer_name)}
-        node.fluid_code.add_layer("absval",
-                                  inputs=input,
-                                  output=node,
-                                  param_attr=attr)
-
     def Accuracy(self, node):
         assert len(
             node.inputs) == 2, 'The count of Accuracy node\'s input is not 2.'
@@ -492,16 +489,6 @@ class CaffeOpMapper(OpMapper):
                                   output=node,
                                   param_attr=attr)
 
-    def TanH(self, node):
-        assert len(
-            node.inputs) == 1, 'The count of TanH node\'s input is not 1.'
-        input = self.graph.get_bottom_node(node, idx=0, copy=True)
-        attr = {'name': string(node.layer_name)}
-        node.fluid_code.add_layer("tanh",
-                                  inputs=input,
-                                  output=node,
-                                  param_attr=attr)
-
     def Eltwise(self, node):
         assert len(
             node.inputs) == 2, 'The count of TanH node\'s input is not 2.'
@@ -892,3 +879,13 @@ class CaffeOpMapper(OpMapper):
                                   is_custom_layer=True)
         if op not in self.used_custom_layers:
             self.used_custom_layers[op] = custom_code
+
+    def directly_map(self, node):
+        assert node.layer_type in self.directly_map_ops
+        op_info = self.directly_map_ops[node.layer_type]
+        input = self.graph.get_bottom_node(node, idx=0, copy=True)
+        attr = {'name': string(node.layer_name)}
+        node.fluid_code.add_layer(op_info,
+                                  inputs=input,
+                                  output=node,
+                                  param_attr=attr)

x2paddle/op_mapper/caffe_shape.py

@@ -74,11 +74,12 @@ def shape_convolution(layer, input_shape):
 
 
 def shape_deconvolution(layer, input_shape):
-    h_i = input_shape[2]
-    w_i = input_shape[3]
+
+    h_i = input_shape[0][2]
+    w_i = input_shape[0][3]
 
     params = layer.convolution_param
-    dila_h, dila_w, pad_h, pad_w, kernel_h, kernel_w, stride_h, stride_w = get_params_w_h(
+    dila_h, dila_w, pad_h, pad_w, kernel_h, kernel_w, stride_h, stride_w = get_kernel_parameters(
         params)
 
     h_o = (h_i - 1) * stride_h - 2 * pad_h + dila_h * (kernel_h - 1) + 1
@@ -124,6 +125,16 @@ def shape_input(layer, input_shape):
     return [list(layer.input_param.shape[0].dim)]
 
 
+def shape_memorydata(layer, input_shape):
+    params = layer.memory_data_param
+    shape = []
+    shape.append(int(params.batch_size))
+    shape.append(int(params.channels))
+    shape.append(int(params.height))
+    shape.append(int(params.width))
+    return [shape]
+
+
 def shape_concat(layer, input_shape):
     params = layer.concat_param
     axis = params.axis