Merge pull request #1 from PaddlePaddle/develop

add

README.md

@@ -5,7 +5,7 @@ X2Paddle支持将其余深度学习框架训练得到的模型，转换至Paddle
 X2Paddle is a toolkit for converting trained model to PaddlePaddle from other deep learning frameworks.
 
 ## 转换模型库
-X2Paddle在多个主流的CV模型上，测试过TensorFlow/Caffe/ONNX模型的转换，可以在[X2Paddle-Model-Zoo](x2paddle_model_zoo.md)查看我们的模型测试列表。如果你在新的模型上进行了测试转换，也欢迎继续补充该列表；如若无法转换，可通过ISSUE反馈给我们，我们会尽快跟进。
+X2Paddle在多个主流的CV模型上，测试过TensorFlow/Caffe/ONNX模型的转换，可以在[X2Paddle-Model-Zoo](x2paddle_model_zoo.md)查看我们的模型测试列表，可以在[OP-LIST](op_list.md)中查看目前X2Paddle支持的OP列表。如果你在新的模型上进行了测试转换，也欢迎继续补充该列表；如若无法转换，可通过ISSUE反馈给我们，我们会尽快跟进。
 
 ## 环境依赖
 
@@ -29,7 +29,7 @@ python setup.py install
 ### 安装方式二
 我们会定期更新pip源上的x2paddle版本
 ```
-pip install x2paddle
+pip install x2paddle --index https://pypi.Python.org/simple/
 ```
 ## 使用方法
 ### TensorFlow
@@ -38,7 +38,7 @@ x2paddle --framework=tensorflow --model=tf_model.pb --save_dir=pd_model
 ```
 ### Caffe
 ```
-x2paddle --framework=caffe --prototxt=deploy.proto --weight=deploy.caffemodel --save_dir=pd_model
+x2paddle --framework=caffe --prototxt=deploy.prototxt --weight=deploy.caffemodel --save_dir=pd_model
 ```
 ### ONNX
 ```

op_list.md

+# X2Paddle支持OP列表
+> 目前X2Paddle支持40+的TensorFlow OP，30+的Caffe Layer，覆盖了大部分CV分类模型常用的操作。我们在如下列表中给出了目前X2Paddle支持的全部OP。
+
+**注：** 目前，部分OP暂未支持，如您在转换过程中出现OP不支持的情况，可自行添加或反馈给我们。欢迎通过[ISSUE反馈](https://github.com/PaddlePaddle/X2Paddle/issues/new)的方式告知我们(模型名，代码实现或模型获取方式)，我们会及时跟进：）
+
+## TensorFlow
+
+| 序号 | OP | 序号 | OP | 序号 | OP | 序号 | OP |
+|------|------|------|------|------|------|------|------|
+| 1  | Relu        | 2  | Relu6     | 3  | Shape     | 4  | Abs                   |
+| 5  | Sigmoid     | 6  | Exp       | 7  | Rsqrt     | 8  | swish_f32             |
+| 9  | Tanh        | 10 | LeakyRelu | 11 | Add       | 12 | RealDiv               |
+| 13 | Sub         | 14 | Maximum   | 15 | Mul       | 16 | FloorDiv              |
+| 17 | Placeholder | 18 | Const     | 19 | Transpose | 20 | FusedBatchNorm        |
+| 21 | Conv2D      | 22 | BiasAdd   | 23 | MaxPool   | 24 | DepthwiseConv2dNative |
+| 25 | Reshape     | 26 | AvgPool   | 27 | SplitV    | 28 | SquaredDifference     |
+| 29 | Tile        | 30 | Pack      | 31 | Pad       | 32 | ResizeBilinear        |
+| 33 | Mean        | 34 | MatMul    | 35 | ArgMax    | 36 | StridedSlice          |
+| 37 | Slice       | 38 | Sum       | 39 | Max       | 40 | Conv2DBackpropInput   |
+| 41 | Cast        | 42 | Split     | 43 | Squeeze   | 44 | ResizeNearestNeighbor |
+| 45 | Softmax     | 46 | Range     | 47 | ConcatV2  |
+
+## Caffe
+
+| 序号 | OP | 序号 | OP | 序号 | OP | 序号 | OP |
+|------|------|------|------|------|------|------|------|
+| 1  | Input     | 2  | Convolution  | 3  | Deconvolution  | 4  | Pooling              |
+| 5  | LRN       | 6  | InnerProduct | 7  | Softmax        | 8  | Slice                |
+| 9  | Concat    | 10 | PReLU        | 11 | Accuracy       | 12 | Eltwise              |
+| 13 | BatchNorm | 14 | Scale        | 15 | Reshape        | 16 | ArgMax               |
+| 17 | Crop      | 18 | Flatten      | 19 | Power          | 20 | Reduction            |
+| 21 | Axpy      | 22 | ROIPolling   | 23 | Permute        | 24 | DetectionOutput      |
+| 25 | Normalize | 26 | Select       | 27 | ShuffleChannel | 28 | ConvolutionDepthwise |
+| 29 | ReLU      | 30 | AbsVal       | 31 | Sigmoid        | 32 | TanH                 |
+
+## ONNX
+
+| 序号 | OP | 序号 | OP | 序号 | OP | 序号 | OP |
+|------|------|------|------|------|------|------|------|
+| 1  | Relu     | 2  | LeakyRelu | 3  | Elu       | 4  | ThresholdedRelu    |
+| 5  | Prelu    | 6  | Tanh      | 7  | Shrink    | 8  | Sigmoid            |
+| 9  | Pow      | 10 | Softplus  | 11 | Softsign  | 12 | HardSigmoid        |
+| 13 | Exp      | 14 | Add       | 15 | Div       | 16 | Sub                |
+| 17 | Mul      | 18 | Shape     | 19 | Clip      | 20 | AveragePool        |
+| 21 | Sqrt     | 22 | ReduceSum | 23 | ReduceMin | 24 | ReduceMean         |
+| 25 | Constant | 26 | Pad       | 27 | Unsqueeze | 28 | Resize             |
+| 29 | Upsample | 30 | Expand    | 31 | Gather    | 32 | Slice              |
+| 33 | Cast     | 34 | Split     | 35 | Reshape   | 36 | ConstantOfShape    |
+| 37 | Ceil     | 38 | Concat    | 39 | Flatten   | 40 | ConvTranspose      |
+| 41 | MatMul   | 42 | Sum       | 43 | Transpose | 44 | BatchNormalization |
+| 45 | Squeeze  | 46 | Equal     | 47 | Identity  | 48 | GlobalAveragePool  |
+| 49 | MaxPool  | 50 | Conv      | 51 | Gemm      |

x2paddle/decoder/tf_decoder.py

@@ -312,6 +312,10 @@ class TFDecoder(object):
 
                 right_shape_been_input = False
                 while not right_shape_been_input:
+                    try:
+                        shape = raw_input(
+                            "Shape of Input(e.g. None,224,224,3): ")
+                    except:
                         shape = input("Shape of Input(e.g. None,224,224,3): ")
                     if shape.count("None") > 1:
                         print("Only 1 dimension can be None, type again:)")

x2paddle/op_mapper/tf_op_mapper.py

@@ -168,7 +168,11 @@ class TFOpMapper(OpMapper):
                 x_input = y
                 y_input = x
                 x_shape = y.out_shapes[0]
+                if len(x_shape) == 0:
+                    x_shape = [1]
                 y_shape = x.out_shapes[0]
+                if len(y_shape) == 0:
+                    y_shape = [1]
             else:
                 if len(x_shape) == 1 and len(y_shape) == 4 and x_shape[
                         0] == y_shape[-1] and y_shape.count(-1) < 1:
@@ -1006,7 +1010,7 @@ class TFOpMapper(OpMapper):
         attr = {
             "bias_attr": False,
             "param_attr": string(kernel.layer_name),
-            "num_filters": k_size[3],
+            "num_filters": k_size[2],
             "filter_size": k_size[0:2],
             "stride": strides[2:4],
             "dilation": dilations[2:4],
@@ -1112,40 +1116,6 @@ class TFOpMapper(OpMapper):
                                   output=node,
                                   param_attr=attr)
 
-    def ResizeNearestNeighbor(self, node):
-        input = self.graph.get_node(node.layer.input[0], copy=True)
-        resize_shape = self.graph.get_node(node.layer.input[1], copy=True)
-        self.add_omit_nodes(resize_shape.layer_name, node.layer_name)
-        if resize_shape.layer_type == "Const":
-            resize_shape = resize_shape.value.tolist()
-        else:
-            resize_shape = self.decoder.infer_shape_tensor(resize_shape)
-        align_corners = node.get_attr("align_corners")
-        attr = {"align_corners": align_corners, "out_shape": resize_shape}
-        node.fluid_code.add_layer("resize_nearest",
-                                  inputs=input,
-                                  output=node,
-                                  param_attr=attr)
-
-    def ResizeBilinear(self, node):
-        input = self.graph.get_node(node.layer.input[0], copy=True)
-        resize_shape = self.graph.get_node(node.layer.input[1], copy=True)
-        self.add_omit_nodes(resize_shape.layer_name, node.layer_name)
-        if resize_shape.layer_type == "Const":
-            resize_shape = resize_shape.value.tolist()
-        else:
-            resize_shape = self.decoder.infer_shape_tensor(resize_shape)
-        align_corners = node.get_attr("align_corners")
-        attr = {
-            "align_corners": align_corners,
-            "out_shape": resize_shape,
-            "align_mode": 1
-        }
-        node.fluid_code.add_layer("resize_bilinear",
-                                  inputs=input,
-                                  output=node,
-                                  param_attr=attr)
-
     def ResizeNearestNeighbor(self, node):
         input = self.graph.get_node(node.layer.input[0], copy=True)
         resize_shape = self.graph.get_node(node.layer.input[1], copy=True)
@@ -1191,37 +1161,6 @@ class TFOpMapper(OpMapper):
                                   output=node,
                                   param_attr=None)
 
-    def RandomUniform(self, node):
-        shape = self.graph.get_node(node.layer.input[0], copy=True)
-        self.add_omit_nodes(shape.layer_name, node.layer_name)
-        if shape.layer_type == "Const":
-            shape = shape.value.tolist()
-        else:
-            shape = self.decoder.infer_shape_tensor(shape)
-        if node.tf_data_format == "NHWC" and len(shape) == 4:
-            shape = [shape[i] for i in [0, 3, 1, 2]]
-        attr = {"shape": shape, "min": 0.0, "max": 0.9999}
-        if shape[0] < 0:
-            input = self.batch_node
-            node.fluid_code.add_layer("uniform_random_batch_size_like",
-                                      inputs=input,
-                                      output=node,
-                                      param_attr=attr)
-        else:
-            node.fluid_code.add_layer("uniform_random",
-                                      inputs=None,
-                                      output=node,
-                                      param_attr=attr)
-
-    def GreaterEqual(self, node):
-        x = self.graph.get_node(node.layer.input[0], copy=True)
-        y = self.graph.get_node(node.layer.input[1], copy=True)
-        inputs = {"x": x, "y": y}
-        node.fluid_code.add_layer("greater_equal",
-                                  inputs=inputs,
-                                  output=node,
-                                  param_attr=None)
-
     def RandomUniform(self, node):
         shape = self.graph.get_node(node.layer.input[0], copy=True)
         self.add_omit_nodes(shape.layer_name, node.layer_name)

x2paddle/op_mapper/tf_op_mapper_nhwc.py

@@ -121,6 +121,25 @@ class TFOpMapperNHWC(OpMapper):
             pd_param_name = list(param.values())[0]
             tf_param = node.get_attr(tf_param_name)
             attr[pd_param_name] = tf_param
+
+        if len(input.out_shapes[0]) == 4 and op_info[0] != 'shape':
+            attr1 = {"perm": [0, 3, 1, 2]}
+            node.fluid_code.add_layer('transpose',
+                                      inputs=input,
+                                      output=node,
+                                      param_attr=attr1)
+            input = node
+            node.fluid_code.add_layer(op_info[0],
+                                      inputs=input,
+                                      output=node,
+                                      param_attr=attr)
+            input = node
+            attr2 = {"perm": [0, 2, 3, 1]}
+            node.fluid_code.add_layer('transpose',
+                                      inputs=input,
+                                      output=node,
+                                      param_attr=attr2)
+        else:
             node.fluid_code.add_layer(op_info[0],
                                       inputs=input,
                                       output=node,
@@ -149,7 +168,11 @@ class TFOpMapperNHWC(OpMapper):
                 x_input = y
                 y_input = x
                 x_shape = y.out_shapes[0]
+                if len(x_shape) == 0:
+                    x_shape = [1]
                 y_shape = x.out_shapes[0]
+                if len(y_shape) == 0:
+                    y_shape = [1]
             else:
                 raise Exception("Unexpected situation happend")
 
@@ -193,6 +216,25 @@ class TFOpMapperNHWC(OpMapper):
                                           output="y_tmp",
                                           param_attr=attr)
                 y_input = "y_tmp"
+        if len(x_shape) == 4 and len(y_shape) == 4:
+            node.fluid_code.add_layer("transpose",
+                                      inputs=x_input,
+                                      output=x_input,
+                                      param_attr={'perm': [0, 3, 1, 2]})
+            node.fluid_code.add_layer("transpose",
+                                      inputs=y_input,
+                                      output=y_input,
+                                      param_attr={'perm': [0, 3, 1, 2]})
+            inputs = {"x": x_input, "y": y_input}
+            node.fluid_code.add_layer(op_type,
+                                      inputs=inputs,
+                                      output=node,
+                                      param_attr=None)
+            node.fluid_code.add_layer("transpose",
+                                      inputs=node,
+                                      output=node,
+                                      param_attr={'perm': [0, 2, 3, 1]})
+        else:
             inputs = {"x": x_input, "y": y_input}
             node.fluid_code.add_layer(op_type,
                                       inputs=inputs,
@@ -965,7 +1007,7 @@ class TFOpMapperNHWC(OpMapper):
         attr = {
             "bias_attr": False,
             "param_attr": string(kernel.layer_name),
-            "num_filters": k_size[3],
+            "num_filters": k_size[2],
             "filter_size": k_size[0:2],
             "stride": strides[2:4],
             "dilation": dilations[2:4],
@@ -978,9 +1020,7 @@ class TFOpMapperNHWC(OpMapper):
 
         if pad_mode == "SAME":
             if node.tf_data_format == "NHWC":
-                print(out_shape)
                 out_shape = [out_shape[i] for i in [0, 3, 1, 2]]
-                print(out_shape)
             for i in range(4):
                 if out_shape[i] < 0:
                     out_shape[i] = 999999

x2paddle_model_zoo.md

@@ -65,3 +65,4 @@
 | mNASNet | [pytorch(personal practice)](https://github.com/rwightman/gen-efficientnet-pytorch) |9|
 | EfficientNet | [pytorch(personal practice)](https://github.com/rwightman/gen-efficientnet-pytorch) |9|
 | SqueezeNet | [onnx official](https://s3.amazonaws.com/download.onnx/models/opset_9/squeezenet.tar.gz) |9|
+|Ultra-Light-Fast-Generic-Face-Detector-1MB| [onnx_model](https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB/tree/master/models/onnx)| |