Skip to content

X
X2Paddle

PaddlePaddle / X2Paddle
大约 1 年 前同步成功

通知 328
Star 698
Fork 167
X
X2Paddle
提交 13aeafee 编写于 作者: S SunAhong1993
浏览文件
操作

release

上级 6e035473
隐藏空白更改
内联 并排
Showing with 266 addition and 457 deletion
README.md
浏览文件 @ 13aeafee
......@@ -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
......@@ -104,21 +106,14 @@ X2Paddle提供了工具解决如下问题，详见[tools/README.md](tools/README
2. [PyTorch预测模型转换教程](./docs/demo/pytorch2paddle.ipynb)
## 更新历史
2020.12.09
1. 新增PyTorch2Paddle转换方式，转换得到Paddle动态图代码，并动转静获得inference_model。
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。
2020.12.09
1. 新增PyTorch2Paddle转换方式，转换得到Paddle动态图代码，并动转静获得inference_model。
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
浏览文件 @ 13aeafee
__version__ = "1.1.0"
__version__ = "1.0.2"
from .core.program import PaddleGraph
......
x2paddle/convert.py
浏览文件 @ 13aeafee
......@@ -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/dygraph/tf2paddle/tf_op_mapper.py
浏览文件 @ 13aeafee
......@@ -13,7 +13,7 @@
# limitations under the License.
from x2paddle.decoder.tf_decoder import TFGraph, TFGraphNode
from x2paddle.core.program import PaddleGraph
from x2paddle.core.program import PaddleGraph
from x2paddle.core.op_mapper import OpMapper
from x2paddle.core.util import *
import traceback
......@@ -58,7 +58,8 @@ class TFOpMapper(OpMapper):
'swish_f32': ['paddle.nn.Swish'],
'Tanh': ['paddle.nn.Tanh'],
'Softplus': ['paddle.nn.Softplus'],
'LeakyRelu': ['paddle.nn.LeakyReLU', dict(alpha='negative_slope')],
'LeakyRelu': ['paddle.nn.LeakyReLU',
dict(alpha='negative_slope')],
'Softmax': ['paddle.nn.Softmax'],
'Floor': ['paddle.floor'],
'Erf': ['paddle.erf'],
......@@ -95,8 +96,7 @@ class TFOpMapper(OpMapper):
self.nn_name2id = dict()
self.input_index = 0
self.inputs_info = dict()
self.paddle_graph = PaddleGraph(
parent_layer=None, graph_type="dygraph", source_type="tf")
self.paddle_graph = PaddleGraph(parent_layer=None, graph_type="dygraph", source_type="tf")
self.paddle_graph.outputs = self.graph.output_nodes
not_placeholder = list()
......@@ -109,7 +109,7 @@ class TFOpMapper(OpMapper):
not_placeholder.append(name)
for name in not_placeholder:
idx = self.graph.input_nodes.index(name)
del self.graph.input_nodes[idx]
del self.graph.input_nodes[idx]
print("Total nodes: {}".format(
sum([
......@@ -134,7 +134,7 @@ class TFOpMapper(OpMapper):
self.paddle_graph.set_name(self.graph.graph_name)
self.paddle_graph.set_parameters(self.params)
self.paddle_graph.set_inputs_info(self.inputs_info)
def op_checker(self):
unsupported_ops = set()
for node_name in self.graph.topo_sort:
......@@ -149,11 +149,11 @@ 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
return False
def directly_map(self, node):
inputs = node.layer.input
......@@ -196,11 +196,8 @@ 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]
self.elementwise_map(node, op_type)
......@@ -211,7 +208,7 @@ class TFOpMapper(OpMapper):
assert len(shape) != 0, "Unknown shape of input nodes[{}].".format(
node.layer_name)
dtype = node.dtype
self.paddle_graph.add_layer(
kernel="paddle.to_tensor",
inputs={},
......@@ -229,15 +226,15 @@ class TFOpMapper(OpMapper):
if value == float('inf'):
value = "float('inf')"
self.paddle_graph.add_layer(
"paddle.full",
inputs={},
"paddle.full",
inputs={},
outputs=[node.name],
dtype=string(dtype),
shape=[1],
fill_value=value)
return
self.params[node.name] = node.value
if 0 not in shape:
self.paddle_graph.add_layer(
"self.create_parameter",
......@@ -247,27 +244,28 @@ class TFOpMapper(OpMapper):
attr=string(node.name),
dtype=string(dtype),
default_initializer="paddle.nn.initializer.Constant(value=0.0)")
def Transpose(self, node):
input = self.graph.get_input_node(node, 0)
perm = self.graph.get_input_node(node, 1)
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(
"paddle.transpose",
inputs={"x": input.name},
outputs=[node.name],
perm=perm)
def Where(self, node):
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)
......@@ -278,10 +276,10 @@ class TFOpMapper(OpMapper):
"x": x.name,
"y": y.name},
outputs=[node.name])
def Neg(self, node):
input = self.graph.get_input_node(node, 0)
self.paddle_graph.add_layer(
"paddle.scale",
inputs={"x": input.name},
......@@ -302,7 +300,10 @@ class TFOpMapper(OpMapper):
layer_attrs["fill_value"] = input_value.value
self.paddle_graph.add_layer(
"paddle.full", inputs=inputs, outputs=[node.name], **layer_attrs)
"paddle.full",
inputs=inputs,
outputs=[node.name],
**layer_attrs)
def DepthToSpace(self, node):
input = self.graph.get_input_node(node, 0)
......@@ -418,8 +419,7 @@ class TFOpMapper(OpMapper):
if kernel.layer_type == 'Const':
kernel_value = kernel.value
else:
kernel_value = self.decoder.infer_tensor(
kernel, use_diff_inputs=False)
kernel_value = self.decoder.infer_tensor(kernel, use_diff_inputs=False)
kernel_weight_name = op_name + ".weight"
self.params[kernel_weight_name] = numpy.transpose(kernel_value,
(3, 2, 0, 1))
......@@ -444,6 +444,7 @@ class TFOpMapper(OpMapper):
outputs=[input_name],
shape=[0, k_size[2], 0, 0])
self.paddle_graph.add_layer(
kernel="paddle.nn.Conv2D",
inputs={"input": input_name},
......@@ -463,7 +464,7 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
perm=[0, 2, 3, 1])
def Conv3D(self, node):
op_name = name_generator("conv", self.nn_name2id)
output_name = node.name
......@@ -484,8 +485,7 @@ class TFOpMapper(OpMapper):
if kernel.layer_type == 'Const':
kernel_value = kernel.value
else:
kernel_value = self.decoder.infer_tensor(
kernel, use_diff_inputs=False)
kernel_value = self.decoder.infer_tensor(kernel, use_diff_inputs=False)
kernel_weight_name = op_name + ".weight"
self.params[kernel_weight_name] = numpy.transpose(kernel_value,
(4, 3, 0, 1, 2))
......@@ -556,7 +556,7 @@ class TFOpMapper(OpMapper):
assert moving_mean.layer_type == "Const"
assert moving_var.layer_type == "Const"
input_name = input.name
input_name = input.name
if data_format == "NHWC":
transpose_name = gen_name("batch_norm", "transpose")
self.paddle_graph.add_layer(
......@@ -567,16 +567,12 @@ class TFOpMapper(OpMapper):
input_name = transpose_name
n, h, w, c = input.out_shapes[0]
else:
n, c, h, w = input.out_shapes[0]
n, c, h, w = input.out_shapes[0]
self.params["{}_{}".format(node.name, gamma.name)] = self.params[
gamma.name]
self.params["{}_{}".format(node.name, beta.name)] = self.params[
beta.name]
self.params["{}_{}".format(node.name, moving_mean.name)] = self.params[
moving_mean.name]
self.params["{}_{}".format(node.name, moving_var.name)] = self.params[
moving_var.name]
self.params["{}_{}".format(node.name, gamma.name)] = self.params[gamma.name]
self.params["{}_{}".format(node.name, beta.name)] = self.params[beta.name]
self.params["{}_{}".format(node.name, moving_mean.name)] = self.params[moving_mean.name]
self.params["{}_{}".format(node.name, moving_var.name)] = self.params[moving_var.name]
self.paddle_graph.add_layer(
kernel="paddle.nn.BatchNorm",
inputs={"input": input_name},
......@@ -585,10 +581,8 @@ class TFOpMapper(OpMapper):
epsilon=node.get_attr("epsilon"),
param_attr=string("{}_{}".format(node.name, gamma.name)),
bias_attr=string("{}_{}".format(node.name, beta.name)),
moving_mean_name=string("{}_{}".format(node.name,
moving_mean.name)),
moving_variance_name=string("{}_{}".format(node.name,
moving_var.name)),
moving_mean_name=string("{}_{}".format(node.name, moving_mean.name)),
moving_variance_name=string("{}_{}".format(node.name, moving_var.name)),
is_test=True)
if data_format == "NHWC":
......@@ -597,7 +591,7 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
perm=[0, 2, 3, 1])
def FusedBatchNormV3(self, node):
self.FusedBatchNorm(node)
......@@ -661,10 +655,11 @@ class TFOpMapper(OpMapper):
outputs=[node.name],
pad=paddings,
value=constant_values)
def MirrorPad(self, node):
self.Pad(node)
def PadV2(self, node):
self.Pad(node)
......@@ -684,7 +679,7 @@ class TFOpMapper(OpMapper):
kernel="paddle.shape",
inputs={"input": input_name},
outputs=[node.name])
def Size(self, node):
input = self.graph.get_input_node(node, 0)
input_name = input.name
......@@ -693,12 +688,15 @@ 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):
......@@ -711,7 +709,7 @@ class TFOpMapper(OpMapper):
inputs={"x": input.name},
outputs=[node.name],
axis=axis)
def TopKV2(self, node):
input = self.graph.get_input_node(node, 0)
k = self.graph.get_input_node(node, 1)
......@@ -767,6 +765,7 @@ class TFOpMapper(OpMapper):
self.params[kernel_weight_name] = numpy.transpose(kernel.value,
(2, 3, 0, 1))
input_name = input.name
if data_format == "NHWC":
in_shape = [in_shape[i] for i in [0, 3, 1, 2]]
......@@ -824,7 +823,7 @@ class TFOpMapper(OpMapper):
op_name = name_generator("pool", self.nn_name2id)
output_name = node.name
layer_outputs = [op_name, output_name]
# TODO(syf): The op has diff.
self.paddle_graph.add_layer(
kernel="paddle.nn.AvgPool2D",
......@@ -834,6 +833,15 @@ class TFOpMapper(OpMapper):
stride=strides[2:4],
padding=string(pad_mode))
# self.paddle_graph.add_layer(
# kernel="fluid.layers.pool2d",
# inputs={"input": input_name},
# outputs=[node.name],
# pool_size=k_size[2:4],
# pool_type=string("avg"),
# pool_stride=strides[2:4],
# pool_padding=string(pad_mode))
if data_format == "NHWC":
self.paddle_graph.add_layer(
kernel="paddle.transpose",
......@@ -876,9 +884,7 @@ 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(
......@@ -904,7 +910,7 @@ class TFOpMapper(OpMapper):
inputs={"x": input_names},
outputs=[node.name],
axis=axis)
def Concat(self, node):
inputs_list = list()
for i in range(1, len(node.inputs)):
......@@ -914,14 +920,14 @@ class TFOpMapper(OpMapper):
axis = axis.value
if axis < 0:
axis += len(inputs_list[0].out_shapes[0])
input_names = [i.name for i in inputs_list]
self.paddle_graph.add_layer(
kernel="paddle.concat",
inputs={"x": input_names},
outputs=[node.name],
axis=axis)
def AddN(self, node):
inputs_list = list()
for i in range(len(node.inputs) - 1):
......@@ -999,7 +1005,7 @@ class TFOpMapper(OpMapper):
new_end.append(999999)
else:
new_end.append(end[i])
if input.dtype == "bool":
self.paddle_graph.add_layer(
"paddle.cast",
......@@ -1014,7 +1020,7 @@ class TFOpMapper(OpMapper):
axes=[i for i in range(len(new_begin))],
starts=new_begin,
ends=new_end)
if input.dtype == "bool":
self.paddle_graph.add_layer(
"paddle.cast",
......@@ -1037,7 +1043,7 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
axis=shrink_axes)
def Prod(self, node):
input = self.graph.get_input_node(node, 0)
reduction_indices = self.graph.get_input_node(node, 1)
......@@ -1067,7 +1073,7 @@ class TFOpMapper(OpMapper):
],
num_or_sections=num_split,
axis=dim)
def SplitV(self, node):
input = self.graph.get_input_node(node, 0)
size_splits = self.graph.get_input_node(node, 1)
......@@ -1076,13 +1082,12 @@ class TFOpMapper(OpMapper):
dim = self.graph.get_input_node(node, 2)
assert dim.layer_type == "Const", "dim of SplitV OP should be Const"
dim = dim.value
self.paddle_graph.add_layer(
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)
......@@ -1098,8 +1103,7 @@ class TFOpMapper(OpMapper):
begin = begin.value.tolist()
attrs['offsets'] = begin
else:
begin = self.decoder.infer_tensor(
begin, use_diff_inputs=False).tolist()
begin = self.decoder.infer_tensor(begin, use_diff_inputs=False).tolist()
attrs['offsets'] = begin
if size.layer_type == "Const":
size = size.value.tolist()
......@@ -1114,18 +1118,19 @@ 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"),
"mode": string("nearest"),
"align_mode": 1
}
attrs = {"align_corners": node.get_attr("align_corners"),
"mode": string("nearest"),
"align_mode": 1}
if resize_shape.layer_type == "Const":
resize_shape = resize_shape.value.tolist()
......@@ -1161,17 +1166,15 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
perm=[0, 2, 3, 1])
def ResizeBilinear(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"),
"mode": string("bilinear"),
"align_mode": 1
}
attrs = {"align_corners": node.get_attr("align_corners"),
"mode": string("bilinear"),
"align_mode": 1}
if resize_shape.layer_type == "Const":
resize_shape = resize_shape.value.tolist()
......@@ -1276,17 +1279,15 @@ 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")
......@@ -1309,20 +1310,30 @@ class TFOpMapper(OpMapper):
perm=[0, 3, 1, 2])
input_name = transpose_name
# TODO(syf): The output_size is not set.
# self.paddle_graph.add_layer(
# kernel="paddle.nn.Conv2DTranspose",
# inputs={"input": input_name},
# outputs=layer_outputs,
# weight_attr=string(kernel_name),
# bias_attr=False,
# in_channels=k_size[3],
# out_channels=k_size[2],
# kernel_size=k_size[0:2],
# stride=strides[2:4],
# dilation=dilations[2:4],
# padding=string(pad_mode))
self.paddle_graph.add_layer(
"self.create_parameter",
inputs={},
outputs=["{}_{}".format(node.name, kernel_name).replace(".", "_")],
shape=self.params[kernel_name].shape,
attr=string(kernel_name))
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],
......@@ -1350,7 +1361,10 @@ 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)
def Range(self, node):
start = self.graph.get_input_node(node, 0)
......@@ -1365,7 +1379,7 @@ class TFOpMapper(OpMapper):
if start.layer_type == "Const":
attr["start"] = start.value
else:
inputs["start"] = start.name
if limit.dtype.startswith('float'):
dtype = limit.dtype
......@@ -1383,7 +1397,10 @@ 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)
def SquaredDifference(self, node):
x = self.graph.get_input_node(node, 0)
......@@ -1394,20 +1411,14 @@ 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)
......@@ -1461,7 +1472,10 @@ 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
......@@ -1482,7 +1496,10 @@ 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(
......@@ -1490,13 +1507,15 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
shape=out_shape)
def GatherNd(self, node):
x = self.graph.get_input_node(node, 0)
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)
......@@ -1511,8 +1530,11 @@ 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)
axis = self.graph.get_input_node(node, 1)
......@@ -1526,114 +1548,7 @@ 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},
outputs=[node.name],
**attrs)
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},
"paddle.flip",
inputs=inputs,
outputs=[node.name],
shape=shape)
**attr)
x2paddle/op_mapper/static/tf2paddle/tf_op_mapper.py
浏览文件 @ 13aeafee
......@@ -13,7 +13,7 @@
# limitations under the License.
from x2paddle.decoder.tf_decoder import TFGraph, TFGraphNode
from x2paddle.core.program import PaddleGraph
from x2paddle.core.program import PaddleGraph
from x2paddle.core.op_mapper import OpMapper
from x2paddle.core.util import *
from x2paddle import program
......@@ -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()
......@@ -136,7 +135,7 @@ class TFOpMapper(OpMapper):
print("\nNodes converted.")
self.paddle_graph.set_name(self.graph.graph_name)
self.paddle_graph.set_parameters(self.params)
def op_checker(self):
unsupported_ops = set()
for node_name in self.graph.topo_sort:
......@@ -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
......@@ -187,11 +186,8 @@ 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]
self.elementwise_map(node, op_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",
......@@ -330,12 +328,14 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
perm=[0, 2, 3, 1])
def Where(self, node):
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)
......@@ -346,10 +346,10 @@ class TFOpMapper(OpMapper):
"x": x.name,
"y": y.name},
outputs=[node.name])
def Neg(self, node):
input = self.graph.get_input_node(node, 0)
self.paddle_graph.add_layer(
"paddle.scale",
inputs={"x": input.name},
......@@ -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)
......@@ -425,7 +424,7 @@ class TFOpMapper(OpMapper):
shape=self.params[kernel_weight_name].shape,
dtype=string(str(self.params[kernel_weight_name].dtype)),
name=string(kernel_weight_name))
input_name = input.name
if data_format == "NHWC":
strides = [strides[i] for i in [0, 3, 1, 2]]
......@@ -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],
......@@ -462,7 +460,7 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
perm=[0, 2, 3, 1])
def Conv3D(self, node):
input = self.graph.get_input_node(node, 0)
kernel = self.graph.get_input_node(node, 1)
......@@ -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)
......@@ -497,7 +494,7 @@ class TFOpMapper(OpMapper):
shape=self.params[kernel_weight_name].shape,
dtype=string(str(self.params[kernel_weight_name].dtype)),
name=string(kernel_weight_name))
input_name = input.name
if data_format == "NDHWC":
strides = [strides[i] for i in [0, 4, 1, 2, 3]]
......@@ -516,12 +513,11 @@ class TFOpMapper(OpMapper):
kernel="paddle.reshape",
inputs={"x": input_name},
outputs=[input_name],
shape=[0, k_size[2], 0, 0, 0])
shape=[0, k_size[2], 0, 0, 0])
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,
"running_mean": moving_mean.name,
"running_var": moving_var.name,
"weight": gamma.name,
"bias": beta.name
},
inputs={"x": input_name,
"running_mean": moving_mean.name,
"running_var": moving_var.name,
"weight": gamma.name,
"bias": beta.name},
outputs=[node.name],
epsilon=node.get_attr("epsilon"))
......@@ -585,7 +579,7 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
perm=[0, 2, 3, 1])
def FusedBatchNormV3(self, node):
self.FusedBatchNorm(node)
......@@ -649,10 +643,11 @@ class TFOpMapper(OpMapper):
outputs=[node.name],
pad=paddings,
value=constant_values)
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):
......@@ -699,7 +697,7 @@ class TFOpMapper(OpMapper):
inputs={"x": input.name},
outputs=[node.name],
axis=axis)
def TopKV2(self, node):
input = self.graph.get_input_node(node, 0)
k = self.graph.get_input_node(node, 1)
......@@ -750,8 +748,8 @@ class TFOpMapper(OpMapper):
if len(kernel.outputs) == 1:
self.params[kernel.name] = numpy.transpose(self.params[kernel.name],
(2, 3, 0, 1))
layer = self.paddle_graph.layers[self.params_output2id[kernel.name]]
(2, 3, 0, 1))
layer = self.paddle_graph.layers[self.params_output2id[kernel.name]]
layer.attrs["shape"] = self.params[kernel.name].shape
else:
self.paddle_graph.add_layer(
......@@ -810,7 +808,7 @@ class TFOpMapper(OpMapper):
strides = [strides[i] for i in [0, 3, 1, 2]]
k_size = [k_size[i] for i in [0, 3, 1, 2]]
input_name = transpose_name
# TODO(syf): The op has diff.
self.paddle_graph.add_layer(
......@@ -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(
......@@ -891,7 +887,7 @@ class TFOpMapper(OpMapper):
inputs={"x": input_names},
outputs=[node.name],
axis=axis)
def Concat(self, node):
inputs_list = list()
for i in range(1, len(node.inputs)):
......@@ -901,14 +897,14 @@ class TFOpMapper(OpMapper):
axis = axis.value
if axis < 0:
axis += len(inputs_list[0].out_shapes[0])
input_names = [i.name for i in inputs_list]
self.paddle_graph.add_layer(
kernel="paddle.concat",
inputs={"x": input_names},
outputs=[node.name],
axis=axis)
def AddN(self, node):
inputs_list = list()
for i in range(len(node.inputs) - 1):
......@@ -986,7 +982,7 @@ class TFOpMapper(OpMapper):
new_end.append(999999)
else:
new_end.append(end[i])
if input.dtype == "bool":
self.paddle_graph.add_layer(
"paddle.cast",
......@@ -1001,7 +997,7 @@ class TFOpMapper(OpMapper):
axes=[i for i in range(len(new_begin))],
starts=new_begin,
ends=new_end)
if input.dtype == "bool":
self.paddle_graph.add_layer(
"paddle.cast",
......@@ -1024,7 +1020,7 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
axis=shrink_axes)
def Prod(self, node):
input = self.graph.get_input_node(node, 0)
reduction_indices = self.graph.get_input_node(node, 1)
......@@ -1054,7 +1050,7 @@ class TFOpMapper(OpMapper):
],
num_or_sections=num_split,
axis=dim)
def SplitV(self, node):
input = self.graph.get_input_node(node, 0)
size_splits = self.graph.get_input_node(node, 1)
......@@ -1063,13 +1059,12 @@ class TFOpMapper(OpMapper):
dim = self.graph.get_input_node(node, 2)
assert dim.layer_type == "Const", "dim of SplitV OP should be Const"
dim = dim.value
self.paddle_graph.add_layer(
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"),
"mode": string("nearest"),
"align_mode": 1
}
attrs = {"align_corners": node.get_attr("align_corners"),
"mode": string("nearest"),
"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"),
"mode": string("bilinear"),
"align_mode": 1
}
attrs = {"align_corners": node.get_attr("align_corners"),
"mode": string("bilinear"),
"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")
......@@ -1300,14 +1299,11 @@ class TFOpMapper(OpMapper):
dtype=string(str(self.params[kernel_name].dtype)),
shape=self.params[kernel_name].shape,
name=string(kernel_name))
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],
......@@ -1332,12 +1328,14 @@ class TFOpMapper(OpMapper):
attr["repeat_times"] = repeat_times
else:
inputs["repeat_times"] = repeat_times.name
self.paddle_graph.add_layer(
kernel="paddle.tile", inputs=inputs, outputs=[node.name], **attr)
if not isinstance(repeat_times,
list) and repeat_times.layer_type != "Const":
kernel="paddle.tile",
inputs=inputs,
outputs=[node.name],
**attr)
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(
......@@ -1489,13 +1490,15 @@ class TFOpMapper(OpMapper):
inputs={"x": node.name},
outputs=[node.name],
shape=out_shape)
def GatherNd(self, node):
x = self.graph.get_input_node(node, 0)
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)
......@@ -1510,8 +1513,11 @@ 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)
axis = self.graph.get_input_node(node, 1)
......@@ -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)
Markdown is supported
0% 或 .
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 或