未验证 提交 108533b2 编写于 作者: S SunAhong1993 提交者: GitHub

Merge pull request #1 from PaddlePaddle/develop

add
...@@ -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 ...@@ -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. X2Paddle is a toolkit for converting trained model to PaddlePaddle from other deep learning frameworks.
## 转换模型库 ## 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 ## 环境依赖
...@@ -29,7 +29,7 @@ python setup.py install ...@@ -29,7 +29,7 @@ python setup.py install
### 安装方式二 ### 安装方式二
我们会定期更新pip源上的x2paddle版本 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 ## 使用方法
### TensorFlow ### TensorFlow
...@@ -38,7 +38,7 @@ x2paddle --framework=tensorflow --model=tf_model.pb --save_dir=pd_model ...@@ -38,7 +38,7 @@ x2paddle --framework=tensorflow --model=tf_model.pb --save_dir=pd_model
``` ```
### Caffe ### 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 ### ONNX
``` ```
......
# 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 |
...@@ -312,7 +312,11 @@ class TFDecoder(object): ...@@ -312,7 +312,11 @@ class TFDecoder(object):
right_shape_been_input = False right_shape_been_input = False
while not right_shape_been_input: while not right_shape_been_input:
shape = input("Shape of Input(e.g. None,224,224,3): ") 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: if shape.count("None") > 1:
print("Only 1 dimension can be None, type again:)") print("Only 1 dimension can be None, type again:)")
else: else:
......
...@@ -168,7 +168,11 @@ class TFOpMapper(OpMapper): ...@@ -168,7 +168,11 @@ class TFOpMapper(OpMapper):
x_input = y x_input = y
y_input = x y_input = x
x_shape = y.out_shapes[0] x_shape = y.out_shapes[0]
if len(x_shape) == 0:
x_shape = [1]
y_shape = x.out_shapes[0] y_shape = x.out_shapes[0]
if len(y_shape) == 0:
y_shape = [1]
else: else:
if len(x_shape) == 1 and len(y_shape) == 4 and x_shape[ if len(x_shape) == 1 and len(y_shape) == 4 and x_shape[
0] == y_shape[-1] and y_shape.count(-1) < 1: 0] == y_shape[-1] and y_shape.count(-1) < 1:
...@@ -1006,7 +1010,7 @@ class TFOpMapper(OpMapper): ...@@ -1006,7 +1010,7 @@ class TFOpMapper(OpMapper):
attr = { attr = {
"bias_attr": False, "bias_attr": False,
"param_attr": string(kernel.layer_name), "param_attr": string(kernel.layer_name),
"num_filters": k_size[3], "num_filters": k_size[2],
"filter_size": k_size[0:2], "filter_size": k_size[0:2],
"stride": strides[2:4], "stride": strides[2:4],
"dilation": dilations[2:4], "dilation": dilations[2:4],
...@@ -1112,40 +1116,6 @@ class TFOpMapper(OpMapper): ...@@ -1112,40 +1116,6 @@ class TFOpMapper(OpMapper):
output=node, output=node,
param_attr=attr) 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): def ResizeNearestNeighbor(self, node):
input = self.graph.get_node(node.layer.input[0], copy=True) input = self.graph.get_node(node.layer.input[0], copy=True)
resize_shape = self.graph.get_node(node.layer.input[1], copy=True) resize_shape = self.graph.get_node(node.layer.input[1], copy=True)
...@@ -1191,37 +1161,6 @@ class TFOpMapper(OpMapper): ...@@ -1191,37 +1161,6 @@ class TFOpMapper(OpMapper):
output=node, output=node,
param_attr=None) 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): def RandomUniform(self, node):
shape = self.graph.get_node(node.layer.input[0], copy=True) shape = self.graph.get_node(node.layer.input[0], copy=True)
self.add_omit_nodes(shape.layer_name, node.layer_name) self.add_omit_nodes(shape.layer_name, node.layer_name)
......
...@@ -121,10 +121,29 @@ class TFOpMapperNHWC(OpMapper): ...@@ -121,10 +121,29 @@ class TFOpMapperNHWC(OpMapper):
pd_param_name = list(param.values())[0] pd_param_name = list(param.values())[0]
tf_param = node.get_attr(tf_param_name) tf_param = node.get_attr(tf_param_name)
attr[pd_param_name] = tf_param attr[pd_param_name] = tf_param
node.fluid_code.add_layer(op_info[0],
inputs=input, if len(input.out_shapes[0]) == 4 and op_info[0] != 'shape':
output=node, attr1 = {"perm": [0, 3, 1, 2]}
param_attr=attr) 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,
param_attr=attr)
def elementwise_map(self, node): def elementwise_map(self, node):
assert node.layer_type in self.elementwise_ops assert node.layer_type in self.elementwise_ops
...@@ -149,7 +168,11 @@ class TFOpMapperNHWC(OpMapper): ...@@ -149,7 +168,11 @@ class TFOpMapperNHWC(OpMapper):
x_input = y x_input = y
y_input = x y_input = x
x_shape = y.out_shapes[0] x_shape = y.out_shapes[0]
if len(x_shape) == 0:
x_shape = [1]
y_shape = x.out_shapes[0] y_shape = x.out_shapes[0]
if len(y_shape) == 0:
y_shape = [1]
else: else:
raise Exception("Unexpected situation happend") raise Exception("Unexpected situation happend")
...@@ -193,11 +216,30 @@ class TFOpMapperNHWC(OpMapper): ...@@ -193,11 +216,30 @@ class TFOpMapperNHWC(OpMapper):
output="y_tmp", output="y_tmp",
param_attr=attr) param_attr=attr)
y_input = "y_tmp" y_input = "y_tmp"
inputs = {"x": x_input, "y": y_input} if len(x_shape) == 4 and len(y_shape) == 4:
node.fluid_code.add_layer(op_type, node.fluid_code.add_layer("transpose",
inputs=inputs, inputs=x_input,
output=node, output=x_input,
param_attr=None) 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,
output=node,
param_attr=None)
def Placeholder(self, node): def Placeholder(self, node):
shape = node.out_shapes[0] shape = node.out_shapes[0]
...@@ -965,7 +1007,7 @@ class TFOpMapperNHWC(OpMapper): ...@@ -965,7 +1007,7 @@ class TFOpMapperNHWC(OpMapper):
attr = { attr = {
"bias_attr": False, "bias_attr": False,
"param_attr": string(kernel.layer_name), "param_attr": string(kernel.layer_name),
"num_filters": k_size[3], "num_filters": k_size[2],
"filter_size": k_size[0:2], "filter_size": k_size[0:2],
"stride": strides[2:4], "stride": strides[2:4],
"dilation": dilations[2:4], "dilation": dilations[2:4],
...@@ -978,9 +1020,7 @@ class TFOpMapperNHWC(OpMapper): ...@@ -978,9 +1020,7 @@ class TFOpMapperNHWC(OpMapper):
if pad_mode == "SAME": if pad_mode == "SAME":
if node.tf_data_format == "NHWC": if node.tf_data_format == "NHWC":
print(out_shape)
out_shape = [out_shape[i] for i in [0, 3, 1, 2]] out_shape = [out_shape[i] for i in [0, 3, 1, 2]]
print(out_shape)
for i in range(4): for i in range(4):
if out_shape[i] < 0: if out_shape[i] < 0:
out_shape[i] = 999999 out_shape[i] = 999999
......
此差异已折叠。
...@@ -65,3 +65,4 @@ ...@@ -65,3 +65,4 @@
| mNASNet | [pytorch(personal practice)](https://github.com/rwightman/gen-efficientnet-pytorch) |9| | mNASNet | [pytorch(personal practice)](https://github.com/rwightman/gen-efficientnet-pytorch) |9|
| EfficientNet | [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| | 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)| |
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册