release

README.md

@@ -33,7 +33,7 @@ X2Paddle的架构设计着重考虑了对多深度学习框架的的支持以及
 - pytorch：torch >=1.5.0 (script方式暂不支持1.7.0)
 
 ## 安装
-### 方式一：源码安装
+### 方式一：源码安装（推荐）
 ```
 git clone https://github.com/PaddlePaddle/X2Paddle.git
 cd X2Paddle
@@ -41,7 +41,7 @@ git checkout develop
 python setup.py install
 ```
 
-### 方式二：pip安装(推荐）
+### 方式二：pip安装
 我们会定期更新pip源上的x2paddle版本
 ```
 pip install x2paddle --index https://pypi.python.org/simple/
@@ -95,8 +95,10 @@ X2Paddle提供了工具解决如下问题，详见[tools/README.md](tools/README
 4. [X2Paddle添加内置的Caffe自定义层](./docs/user_guides/add_caffe_custom_layer.md)
 5. [转换后PaddlePaddle预测模型简介](./docs/user_guides/pd_folder_introduction.py)
 6. [Paddle到ONNX的转换](https://github.com/PaddlePaddle/Paddle2ONNX)
-7. [X2Paddle测试模型库](./docs/introduction/x2paddle_model_zoo.md)  
-8. [X2Paddle支持的op列表](./docs/introduction/op_list.md)
+
+## 支持列表文档
+1. [X2Paddle测试模型库](./docs/introduction/x2paddle_model_zoo.md)  
+2. [X2Paddle支持的op列表](./docs/introduction/op_list.md)
 
 
 ## 转换教程
@@ -109,16 +111,9 @@ X2Paddle提供了工具解决如下问题，详见[tools/README.md](tools/README
   方式一：trace方式，转换后的代码有模块划分，每个模块的功能与PyTorch相同。
   方式二：script方式，转换后的代码按执行顺序逐行出现。
 2. 新增Caffe/ONNX/Tensorflow到Paddle动态图的转换。
-3. 新增TensorFlow op映射（14个）：Neg、Greater、FloorMod、LogicalAdd、Prd、Equal、Conv3D、Ceil、AddN、DivNoNan、Where、MirrorPad、Size、TopKv2。
+3. 新增TensorFlow op（14个）：Neg、Greater、FloorMod、LogicalAdd、Prd、Equal、Conv3D、Ceil、AddN、DivNoNan、Where、MirrorPad、Size、TopKv2
 4. 新增Optimizer模块，主要包括op融合、op消除功能，转换后的代码可读性更强，进行预测时耗时更短。
 
-2021.04.30
-1. 新增支持转换的模型：[SwinTransformer](https://github.com/microsoft/Swin-Transformer/)、[BASNet](https://github.com/xuebinqin/BASNet)、[DBFace](https://github.com/dlunion/DBFace)、[EasyOCR](https://github.com/JaidedAI/EasyOCR)、[CifarNet](https://github.com/tensorflow/models/blob/master/research/slim/nets/cifarnet.py)等。
-2. 支持Windows上使用本工具。
-3. 新增TensorFlow op映射（4个）：SplitV、ReverseV2、BatchToSpaceND、SpaceToBatchND。
-4. 新增PyTorch op映射（11个）：aten::index、aten::roll、aten::adaptive_avg_pool1d、aten::reflection_pad2d、aten::reflection_pad1d、aten::instance_norm、aten::gru、aten::norm、aten::clamp_min、aten:prelu、aten:split_with_sizes。
-5. 新增ONNX op映射（1个）：DepthToSpace。
-6. 新增Caffe op映射（1个）：op：MemoryData。
 
 ## 贡献代码
 

x2paddle/__init__.py

-__version__ = "1.1.0"
+__version__ = "1.0.2"
 
 from .core.program import PaddleGraph
 

x2paddle/convert.py

@@ -41,6 +41,7 @@ def arg_parser():
     parser.add_argument(
         "--save_dir",
         "-s",
+        required=True,
         type=_text_type,
         default=None,
         help="path to save translated model")
@@ -220,8 +221,6 @@ def main():
             x2paddle.__version__))
         return
 
-    assert args.save_dir is not None, "--save_dir is not defined"
-
     try:
         import platform
         v0, v1, v2 = platform.python_version().split('.')

x2paddle/op_mapper/static/tf2paddle/tf_op_mapper.py

@@ -60,8 +60,8 @@ class TFOpMapper(OpMapper):
         'swish_f32': ['paddle.nn.functional.swish'],
         'Tanh': ['paddle.tanh'],
         'Softplus': ['paddle.nn.functional.softplus'],
-        'LeakyRelu':
-        ['paddle.nn.functional.leaky_relu', dict(alpha='negative_slope')],
+        'LeakyRelu': ['paddle.nn.functional.leaky_relu', 
+                     dict(alpha='negative_slope')],
         'Floor': ['paddle.floor'],
         'Erf': ['paddle.erf'],
         'Square': ['paddle.square']
@@ -95,8 +95,7 @@ class TFOpMapper(OpMapper):
         if not self.op_checker():
             raise Exception("Model is not supported yet.")
         self.params = dict()
-        self.paddle_graph = PaddleGraph(
-            parent_layer=None, graph_type="static", source_type="tf")
+        self.paddle_graph = PaddleGraph(parent_layer=None, graph_type="static", source_type="tf")
         self.params_output2id = dict()
 
         not_placeholder = list()
@@ -151,8 +150,8 @@ class TFOpMapper(OpMapper):
             return True
         else:
             if len(unsupported_ops) > 0:
-                print("\n========= {} OPs are not supported yet ===========".
-                      format(len(unsupported_ops)))
+                print("\n========= {} OPs are not supported yet ===========".format(
+                    len(unsupported_ops)))
             for op in unsupported_ops:
                 print("========== {} ============".format(op))
             return False
@@ -187,10 +186,7 @@ class TFOpMapper(OpMapper):
             inputs={"x": x.name,
                     "y": y.name},
             outputs=[node.name])
-        self.paddle_graph.layers[layer_id].input_shapes = {
-            "x": x_shape,
-            "y": y_shape
-        }
+        self.paddle_graph.layers[layer_id].input_shapes = {"x": x_shape, "y": y_shape}
         
     def bool_map(self, node):
         op_type = self.bool_ops[node.layer_type]
@@ -245,8 +241,7 @@ class TFOpMapper(OpMapper):
         if perm.layer_type == "Const":
             perm = perm.value.tolist()
         else:
-            perm = self.decoder.infer_tensor(
-                perm, use_diff_inputs=False).tolist()
+            perm = self.decoder.infer_tensor(perm, use_diff_inputs=False).tolist()
 
         self.paddle_graph.add_layer(
             kernel="paddle.transpose",
@@ -268,7 +263,10 @@ class TFOpMapper(OpMapper):
         attr["fill_value"] = input_value.value
 
         self.paddle_graph.add_layer(
-            "paddle.full", inputs=inputs, outputs=[node.name], **attr)
+            "paddle.full",
+            inputs=inputs,
+            outputs=[node.name],
+            **attr)
         if dims.layer_type != "Const":
             self.paddle_graph.add_layer(
                 "paddle.reshape",
@@ -335,7 +333,9 @@ class TFOpMapper(OpMapper):
         if len(node.layer.input) == 1:
             cond = self.graph.get_input_node(node, 0)
             self.paddle_graph.add_layer(
-                "paddle.nonzero", inputs={"x": cond.name}, outputs=[node.name])
+                "paddle.nonzero",
+                inputs={"x": cond.name},
+                outputs=[node.name])
         else:
             cond = self.graph.get_input_node(node, 0)
             x = self.graph.get_input_node(node, 1)
@@ -409,8 +409,7 @@ class TFOpMapper(OpMapper):
             kernel_value = kernel.value
             kernel_weight_name = kernel.name.replace('/', '_')
         else:
-            kernel_value = self.decoder.infer_tensor(
-                kernel, use_diff_inputs=False)
+            kernel_value = self.decoder.infer_tensor(kernel, use_diff_inputs=False)
             if kernel.layer_type == 'Split':
                 kernel_weight_name = "{}_{}_kernel".format(node.name,
                                                            kernel.name)
@@ -448,8 +447,7 @@ class TFOpMapper(OpMapper):
 
         self.paddle_graph.add_layer(
             kernel="paddle.nn.functional.conv2d",
-            inputs={"x": input_name,
-                    "weight": kernel_weight_name},
+            inputs={"x": input_name, "weight": kernel_weight_name},
             outputs=[node.name],
             bias=None,
             stride=strides[2:4],
@@ -481,8 +479,7 @@ class TFOpMapper(OpMapper):
             kernel_value = kernel.value
             kernel_weight_name = kernel.name.replace('/', '_')
         else:
-            kernel_value = self.decoder.infer_tensor(
-                kernel, use_diff_inputs=False)
+            kernel_value = self.decoder.infer_tensor(kernel, use_diff_inputs=False)
             if kernel.layer_type == 'Split':
                 kernel_weight_name = "{}_{}_kernel".format(node.name,
                                                            kernel.name)
@@ -520,8 +517,7 @@ class TFOpMapper(OpMapper):
             
         self.paddle_graph.add_layer(
             kernel="paddle.nn.functional.conv3d",
-            inputs={"x": input_name,
-                    "weight": kernel_weight_name},
+            inputs={"x": input_name,  "weight": kernel_weight_name},
             outputs=[node.name],
             bias=None,
             stride=strides[2:5],
@@ -569,13 +565,11 @@ class TFOpMapper(OpMapper):
 
         self.paddle_graph.add_layer(
             kernel="paddle.nn.functional.batch_norm",
-            inputs={
-                "x": input_name,
+            inputs={"x": input_name,
                     "running_mean": moving_mean.name,
                     "running_var": moving_var.name,
                     "weight": gamma.name,
-                "bias": beta.name
-            },
+                    "bias": beta.name},
             outputs=[node.name],
             epsilon=node.get_attr("epsilon"))
 
@@ -653,6 +647,7 @@ class TFOpMapper(OpMapper):
     def MirrorPad(self, node):
         self.Pad(node)
         
+        
     def PadV2(self, node):
         self.Pad(node)
 
@@ -681,12 +676,15 @@ class TFOpMapper(OpMapper):
             inputs={"input": input_name},
             outputs=[node.name])
         self.paddle_graph.add_layer(
-            kernel="paddle.prod", inputs={"x": node.name}, outputs=[node.name])
+            kernel="paddle.prod",
+            inputs={"x": node.name},
+            outputs=[node.name])
         
     def Ceil(self, node):
         input = self.graph.get_input_node(node, 0)
         self.paddle_graph.add_layer(
-            kernel="paddle.ceil", inputs={"x": input.name},
+            kernel="paddle.ceil",
+            inputs={"x": input.name},
             outputs=[node.name])
 
     def ArgMax(self, node):
@@ -863,9 +861,7 @@ class TFOpMapper(OpMapper):
                 axis = 1
             else:
                 raise Exception("Unexpected situation happend in Unpack OP")
-        layer_outputs = [
-            "{}_p{}".format(node.layer_name, i) for i in range(num)
-        ]
+        layer_outputs = ["{}_p{}".format(node.layer_name, i) for i in range(num)]
         if len(layer_outputs) == 1:
             layer_outputs[0] = "[{}]".format(node.layer_name)
         self.paddle_graph.add_layer(
@@ -1068,8 +1064,7 @@ class TFOpMapper(OpMapper):
             kernel="paddle.split",
             inputs={"x": input.name},
             outputs=[
-                "{}_p{}".format(node.layer_name, i)
-                for i in range(len(size_splits))
+                "{}_p{}".format(node.layer_name, i) for i in range(len(size_splits))
             ],
             num_or_sections=size_splits,
             axis=dim)
@@ -1085,8 +1080,15 @@ class TFOpMapper(OpMapper):
             begin = begin.value.tolist()
             attrs['offsets'] = begin
         else:
-            begin = self.decoder.infer_tensor(
-                begin, use_diff_inputs=False).tolist()
+            #             shape = begin.out_shapes[0]
+            #             reshape_name = gen_name("slice", "reshape")
+            #             self.paddle_graph.add_layer(
+            #                 kernel="fluid.layers.reshape",
+            #                 inputs={"x": begin.name},
+            #                 outputs=[reshape_name],
+            #                 shape=shape)
+            #             inputs['offsets'] = reshape_name
+            begin = self.decoder.infer_tensor(begin, use_diff_inputs=False).tolist()
             attrs['offsets'] = begin
         if size.layer_type == "Const":
             size = size.value.tolist()
@@ -1101,18 +1103,19 @@ class TFOpMapper(OpMapper):
                 shape=shape)
             inputs['shape'] = reshape_name
         self.paddle_graph.add_layer(
-            kernel="paddle.crop", inputs=inputs, outputs=[node.name], **attrs)
+            kernel="paddle.crop",
+            inputs=inputs,
+            outputs=[node.name],
+            **attrs)
 
     def ResizeNearestNeighbor(self, node):
         input = self.graph.get_input_node(node, 0)
         resize_shape = self.graph.get_input_node(node, 1)
         data_format = "NHWC"
         inputs = {"x": input.name}
-        attrs = {
-            "align_corners": node.get_attr("align_corners"),
+        attrs = {"align_corners": node.get_attr("align_corners"),
                  "mode": string("nearest"),
-            "align_mode": 1
-        }
+                 "align_mode": 1}
 
         if resize_shape.layer_type == "Const":
             resize_shape = resize_shape.value.tolist()
@@ -1154,11 +1157,9 @@ class TFOpMapper(OpMapper):
         resize_shape = self.graph.get_input_node(node, 1)
         data_format = "NHWC"
         inputs = {"x": input.name}
-        attrs = {
-            "align_corners": node.get_attr("align_corners"),
+        attrs = {"align_corners": node.get_attr("align_corners"),
                  "mode": string("bilinear"),
-            "align_mode": 1
-        }
+                 "align_mode": 1}
 
         if resize_shape.layer_type == "Const":
             resize_shape = resize_shape.value.tolist()
@@ -1260,17 +1261,15 @@ class TFOpMapper(OpMapper):
         if out_shape.layer_type == "Const":
             out_shape = out_shape.value.tolist()
         else:
-            out_shape = self.decoder.infer_tensor(
-                out_shape, out_shape=node.out_shapes[0])
+            out_shape = self.decoder.infer_tensor(out_shape,
+                                                  out_shape=node.out_shapes[0])
 
         in_shape = input.out_shapes[0]
         if in_shape.count(-1) > 2:
-            in_shape = self.decoder.infer_tensor(
-                input, use_diff_inputs=False).shape
+            in_shape = self.decoder.infer_tensor(input, use_diff_inputs=False).shape
         k_size = kernel.out_shapes[0]
         if k_size.count(-1) > 2:
-            k_size = self.decoder.infer_tensor(
-                kernel, use_diff_inputs=False).shape
+            k_size = self.decoder.infer_tensor(kernel, use_diff_inputs=False).shape
 
         pad_mode = node.get_attr("padding").decode()
         strides = node.get_attr("strides")
@@ -1303,11 +1302,8 @@ class TFOpMapper(OpMapper):
     
         self.paddle_graph.add_layer(
             kernel="paddle.nn.functional.conv2d_transpose",
-            inputs={
-                "x": input_name,
-                "weight":
-                "{}_{}".format(node.name, kernel_name).replace(".", "_")
-            },
+            inputs={"x": input_name,
+                    "weight": "{}_{}".format(node.name, kernel_name).replace(".", "_")},
             outputs=[node.name],
             bias=None,
             stride=strides[2:4],
@@ -1334,10 +1330,12 @@ class TFOpMapper(OpMapper):
             inputs["repeat_times"] = repeat_times.name
             
         self.paddle_graph.add_layer(
-            kernel="paddle.tile", inputs=inputs, outputs=[node.name], **attr)
+            kernel="paddle.tile",
+            inputs=inputs,
+            outputs=[node.name],
+            **attr)
         
-        if not isinstance(repeat_times,
-                          list) and repeat_times.layer_type != "Const":
+        if not isinstance(repeat_times, list) and repeat_times.layer_type != "Const":
             self.paddle_graph.add_layer(
                 kernel="paddle.reshape",
                 inputs={"x": node.name},
@@ -1374,7 +1372,10 @@ class TFOpMapper(OpMapper):
         attr["dtype"] = string(node.dtype)
 
         self.paddle_graph.add_layer(
-            kernel="paddle.arange", inputs=inputs, outputs=[node.name], **attr)
+            kernel="paddle.arange",
+            inputs=inputs,
+            outputs=[node.name],
+            **attr)
         if start.layer_type != "Const" or \
                 limit.layer_type != "Const" or \
                 delta.layer_type != "Const":
@@ -1393,20 +1394,14 @@ class TFOpMapper(OpMapper):
         # TODO(syf)
         layer_id = self.paddle_graph.add_layer(
             "paddle.subtract", inputs=inputs, outputs=[node.name])
-        self.paddle_graph.layers[layer_id].input_shapes = {
-            "x": x_shape,
-            "y": y_shape
-        }
+        self.paddle_graph.layers[layer_id].input_shapes = {"x": x_shape, "y": y_shape}
 
         inputs = {"x": node.name, "y": node.name}
         x_shape = node.out_shapes[0]
         y_shape = node.out_shapes[0]
         layer_id = self.paddle_graph.add_layer(
             "paddle.multiply", inputs=inputs, outputs=[node.name])
-        self.paddle_graph.layers[layer_id].input_shapes = {
-            "x": x_shape,
-            "y": y_shape
-        }
+        self.paddle_graph.layers[layer_id].input_shapes = {"x": x_shape, "y": y_shape}
 
     def OneHot(self, node):
         input = self.graph.get_input_node(node, 0)
@@ -1460,7 +1455,10 @@ class TFOpMapper(OpMapper):
                 outputs=[input_name],
                 dtype=string("bool"))
         self.paddle_graph.add_layer(
-            "paddle.all", inputs={"x": input_name}, outputs=[node.name], **attr)
+            "paddle.all",
+            inputs={"x": input_name},
+            outputs=[node.name],
+            **attr)
 
         node.layer.attr['dtype'].type = 10
 
@@ -1481,7 +1479,10 @@ class TFOpMapper(OpMapper):
                 shape=[-1])
         inputs = {'x': embeddings.name, 'index': index_name}
         self.paddle_graph.add_layer(
-            "paddle.gather", inputs=inputs, outputs=[node.name], axis=axis)
+            "paddle.gather",
+            inputs=inputs,
+            outputs=[node.name],
+            axis=axis)
         if len(index.out_shapes[0]) != 1:
             out_shape = node.out_shapes[0]
             self.paddle_graph.add_layer(
@@ -1495,7 +1496,9 @@ class TFOpMapper(OpMapper):
         index = self.graph.get_input_node(node, 1)
         inputs = {'x': x.name, 'index': index.name}
         self.paddle_graph.add_layer(
-            "paddle.gather_nd", inputs=inputs, outputs=[node.name])
+            "paddle.gather_nd",
+            inputs=inputs,
+            outputs=[node.name])
 
     def ExpandDims(self, node):
         x = self.graph.get_input_node(node, 0, copy=True)
@@ -1510,7 +1513,10 @@ class TFOpMapper(OpMapper):
         else:
             inputs['axis'] = y.name
         self.paddle_graph.add_layer(
-            "paddle.unsqueeze", inputs=inputs, outputs=[node.name], **attr)
+            "paddle.unsqueeze",
+            inputs=inputs,
+            outputs=[node.name],
+            **attr)
         
     def ReverseV2(self, node):
         x = self.graph.get_input_node(node, 0)
@@ -1525,114 +1531,8 @@ class TFOpMapper(OpMapper):
         else:
             inputs['axis'] = axis.name
         self.paddle_graph.add_layer(
-            "paddle.flip", inputs=inputs, outputs=[node.name], **attr)
-
-    def BatchToSpaceND(self, node):
-        '''
-        reshape->transpose->reshape->crop
-        '''
-        x = self.graph.get_input_node(node, 0)
-        block_shape = self.graph.get_input_node(node, 1)
-        crops = self.graph.get_input_node(node, 2)
-        if block_shape.layer_type == "Const":
-            block_shape = block_shape.value.tolist()
-        if crops.layer_type == "Const":
-            crops = crops.value.tolist()
-        data_format = x.get_attr("data_format").decode()
-        if data_format == "NHWC":
-            n, h, w, c = x.out_shapes[0]
-        else:
-            n, c, h, w = x.out_shapes[0]
-        input_name = x.name
-        #reshape
-        shape = block_shape + [-1, h, w, c]
-        reshape_name = gen_name("batch_to_space", "reshape")
-        self.paddle_graph.add_layer(
-            kernel="paddle.reshape",
-            inputs={"x": input_name},
-            outputs=[reshape_name],
-            shape=shape)
-        #transpose
-        perm = [len(block_shape)] + list(j for i in range(len(block_shape)) for j in (i + len(block_shape) + 1, i)) +\
-                                    list(i + 2*len(block_shape) + 1 for i in range(len(x.out_shapes[0]) - len(block_shape) - 1))
-        transpose_name = gen_name("batch_to_space", "transpose")
-        self.paddle_graph.add_layer(
-            kernel="paddle.transpose",
-            inputs={"x": reshape_name},
-            outputs=[transpose_name],
-            perm=perm)
-        #reshape
-        shape = [-1] + list(i * j
-                            for i, j in zip(block_shape, x.out_shapes[0][
-                                1:])) + x.out_shapes[0][1 + len(block_shape):]
-        reshape_name = gen_name("batch_to_space", "reshape")
-        self.paddle_graph.add_layer(
-            kernel="paddle.reshape",
-            inputs={"x": transpose_name},
-            outputs=[reshape_name],
-            shape=shape)
-        #crop
-        attrs = {}
-        crop_shape = shape
-        crop_offsets = [0] * len(shape)
-        for i in range(len(crops)):
-            crop_shape[i + 1] = crop_shape[i + 1] - crops[i][0] - crops[i][1]
-            crop_offsets[i + 1] = crops[i][0]
-        attrs['shape'] = crop_shape
-        attrs['offsets'] = crop_offsets
-        self.paddle_graph.add_layer(
-            kernel="paddle.crop",
-            inputs={"x": reshape_name},
+            "paddle.flip",
+            inputs=inputs,
             outputs=[node.name],
-            **attrs)
+            **attr)
 
-    def SpaceToBatchND(self, node):
-        '''
-        zero-pad->reshape->transpose->reshape
-        '''
-        x = self.graph.get_input_node(node, 0)
-        block_shape = self.graph.get_input_node(node, 1)
-        paddings = self.graph.get_input_node(node, 2)
-        if block_shape.layer_type == "Const":
-            block_shape = block_shape.value.tolist()
-        if paddings.layer_type == "Const":
-            paddings = paddings.value.flatten().tolist()
-        input_name = x.name
-        #zero-pad
-        constant_values = 0
-        pad_name = gen_name("space_to_batch", "pad")
-        paddings = [0, 0] + paddings + [0, 0]
-        self.paddle_graph.add_layer(
-            kernel="paddle.nn.functional.pad",
-            inputs={"x": input_name},
-            outputs=[pad_name],
-            pad=paddings,
-            value=constant_values)
-        #reshape
-        n, h, w, c = x.out_shapes[0]
-        h = h + paddings[2] + paddings[3]
-        w = w + paddings[4] + paddings[5]
-        shape = [
-            n, h // block_shape[0], block_shape[0], w // block_shape[1],
-            block_shape[1], c
-        ]
-        reshape_name = gen_name("space_to_batch", "reshape")
-        self.paddle_graph.add_layer(
-            kernel="paddle.reshape",
-            inputs={"x": pad_name},
-            outputs=[reshape_name],
-            shape=shape)
-        #transpose
-        transpose_name = gen_name("space_to_batch", "transpose")
-        self.paddle_graph.add_layer(
-            kernel="paddle.transpose",
-            inputs={"x": reshape_name},
-            outputs=[transpose_name],
-            perm=[2, 4, 0, 1, 3, 5])
-        #reshape
-        shape = [-1, h // block_shape[0], w // block_shape[1], c]
-        self.paddle_graph.add_layer(
-            kernel="paddle.reshape",
-            inputs={"x": transpose_name},
-            outputs=[node.name],
-            shape=shape)