Merge pull request #443 from SunAhong1993/paddle-2.0-new

fix the conv2dtranspose

x2paddle/op_mapper/dygraph/pytorch2paddle/aten.py

@@ -14,6 +14,7 @@
 # limitations under the License.
 
 import copy
+import numpy as np
 from x2paddle.core.util import *
 from x2paddle.core.program import PaddleGraph
 
@@ -926,7 +927,7 @@ def aten_conv2d(mapper, graph, node):
         %27 (Tensor): bias。
         %28 (int): 步长大小。
         %29 (int): 填充大小。
-        %30 (int): 膨胀系数大小。
+        %30 (int): 空洞大小。
         %26 (int): 卷积的组数。
     """
     scope_name = mapper.normalize_scope_name(node)
@@ -988,7 +989,7 @@ def aten__convolution(mapper, graph, node):
         %10 (Tensor): bias。
         %19 (list): 步长大小。
         %20 (list): 填充大小。
-        %21 (list): 膨胀系数大小。
+        %21 (list): 空洞大小。
         %13 (bool): 是否进行转置卷积。
         %22 (list): 输出形状上一侧额外添加的大小。
         %12 (int): 卷积的组数。
@@ -1009,7 +1010,10 @@ def aten__convolution(mapper, graph, node):
     current_inputs = list(layer_inputs.values())
     # 处理输入1，即%18
     weights = mapper.pytorch_params[inputs_name[1]]
-    mapper.paddle_params[op_name + ".weight"] = weights
+    mapper.paddle_params[op_name + ".weight"] = weights #np.swapaxes(weights, 0, 1)
+    if mapper.attrs[inputs_name[6]]:
+        layer_attrs["out_channels"] = weights.shape[1]
+    else:
         layer_attrs["out_channels"] = weights.shape[0]
     layer_attrs["kernel_size"] = weights.shape[2:]    
     # 处理输入2，即%10
@@ -1033,6 +1037,10 @@ def aten__convolution(mapper, graph, node):
         layer_attrs["output_padding"] = mapper.attrs[inputs_name[7]]
     # 处理输入8，即%12
     layer_attrs["groups"] = mapper.attrs[inputs_name[8]]
+    if mapper.attrs[inputs_name[6]]:
+        layer_attrs['in_channels'] = weights.shape[0] * mapper.attrs[inputs_name[
+            8]]
+    else:
         layer_attrs['in_channels'] = weights.shape[1] * mapper.attrs[inputs_name[
             8]]
     if mapper.attrs[inputs_name[6]]:
@@ -1052,6 +1060,71 @@ def aten__convolution(mapper, graph, node):
     return current_inputs, current_outputs
 
 
+def aten_conv_transpose2d(mapper, graph, node):
+    """ 构造conv_transpose2d的PaddleLayer。
+
+    TorchScript示例:
+        %input.10 : Tensor = aten::conv_transpose2d(%input.1, %18, %10, %19, %20, %21, %13, %22)
+        参数含义:
+        %input.10 (Tensor): 输出，卷积后的结果。
+        %input.8 (Tensor): 需要进行卷积的特征层。
+        %18 (Tensor): weights。
+        %10 (Tensor): bias。
+        %19 (list): 步长大小。
+        %20 (list): 填充大小。
+        %21 (int/tuple): 输出形状上一侧额外添加的大小。
+        %13 (int): 二维卷积层的组数。
+        %22 (int/tuple): 空洞大小。
+    """
+    scope_name = mapper.normalize_scope_name(node)
+    op_name = name_generator("conv2d", mapper.nn_name2id)
+    output_name = mapper._get_outputs_name(node)[0]
+    layer_outputs = [op_name, output_name]
+    layer_inputs = {}
+    layer_attrs = {}
+    inputs_name, inputs_node = mapper._get_inputs_name(node)
+    # 获取当前节点输出的list
+    current_outputs = [output_name]
+    # 处理输入0，即%input.8
+    mapper._check_input(graph, inputs_node[0], inputs_name[0], current_outputs, scope_name)
+    layer_inputs["input"] = inputs_name[0]
+    # 获取当前节点输入的list
+    current_inputs = list(layer_inputs.values())
+    # 处理输入1，即%18
+    weights = mapper.pytorch_params[inputs_name[1]]
+    mapper.paddle_params[op_name + ".weight"] = weights
+    layer_attrs["out_channels"] = weights.shape[1]
+    layer_attrs["kernel_size"] = weights.shape[2:]
+    # 处理输入2，即%10
+    if inputs_name[2] in mapper.pytorch_params:
+        bias = mapper.pytorch_params[inputs_name[2]]
+        if bias is not None:
+            mapper.paddle_params[op_name + ".bias"] = bias
+        else:
+            layer_attrs["bias_attr"] = False
+    else:
+        layer_attrs["bias_attr"] = False
+    # 处理输入3，即%19
+    layer_attrs["stride"] = mapper.attrs[inputs_name[3]]
+    # 处理输入4，即%20
+    layer_attrs["padding"] = mapper.attrs[inputs_name[4]]
+    # 处理输入5，即%21
+    layer_attrs["output_padding"] = mapper.attrs[inputs_name[5]]
+    # 处理输入6，即%13
+    layer_attrs["groups"] = mapper.attrs[inputs_name[6]]
+    # 处理输入7，即%22
+    layer_attrs["dilation"] = mapper.attrs[inputs_name[7]]
+    layer_attrs['in_channels'] = weights.shape[0] * mapper.attrs[inputs_name[
+            6]]
+    graph.add_layer(
+        "paddle.nn.Conv2DTranspose",
+        inputs=layer_inputs,
+        outputs=layer_outputs,
+        scope_name=scope_name,
+        **layer_attrs)
+    return current_inputs, current_outputs
+
+
 def aten_cos(mapper, graph, node):
     """ 构造数学计算cos的PaddleLayer。
 

x2paddle/optimizer/code_optimizer/layer_code_generator.py

@@ -21,6 +21,7 @@ NN_KERNEL_NAME = {"paddle.nn.BatchNorm": "bn",
                   "paddle.nn.Conv2D": "conv",
                   "paddle.nn.Embedding": "embedding",
                   "paddle.nn.Linear": "linear",
+                  "paddle.nn.Conv2DTranspose": "conv",
                   "paddle.nn.ReLU": "relu",
                   "paddle.nn.ReLU6": "relu",
                   "paddle.nn.Softmax": "softmax",
@@ -35,7 +36,7 @@ NN_KERNEL_NAME = {"paddle.nn.BatchNorm": "bn",
                   "paddle.nn.GELU": "gelu",
                   "paddle.nn.Hardtanh": "tanh",
                   "paddle.nn.LeakyReLU": "leakly_relu"}
-NN_KERNEL_WITH_PARAMS = list(NN_KERNEL_NAME.keys())[:5]
+NN_KERNEL_WITH_PARAMS = list(NN_KERNEL_NAME.keys())[:6]
 
 def rename_layers(layers, param_tree=None):
     """ 对子模块的输入输出等进行重命名。

x2paddle/optimizer/fusion/dygraph/interpolate_bilinear_fuser.py

@@ -22,13 +22,7 @@ from x2paddle.core.util import *
 class DygraphInterpolateBilinearFuser(FuseBase):
     def __init__(self):
         super(DygraphInterpolateBilinearFuser, self).__init__(graph_type="dygraph")
-        import torch
-        torch_version = torch.__version__
-        torch_version_part = torch_version.split(".")
-        if int(torch_version_part[0]) == 1 and int(torch_version_part[1]) > 5:
-            self.version_gt_150 = True
-        else:
-            self.version_gt_150 = False
+        self.pattenrs = list()
 
     def build_pattern(self):
         """ 描述需要替换的双线性插值图结构。
@@ -72,27 +66,27 @@ class DygraphInterpolateBilinearFuser(FuseBase):
         def gen_name(id):
             return "x" + str(id)
 
-        if self.version_gt_150:
-            self.pattern.add_layer(
+        pattern = PaddleGraph(graph_type="dygraph")
+        pattern.add_layer(
             "prim.shape",
             inputs={"input": "interpolate-input-0"},
             outputs=[gen_name(9)])
-            self.pattern.add_layer(
+        pattern.add_layer(
             "prim.len",
             inputs={"input": gen_name(9)},
             outputs=[gen_name(9)])
-            self.pattern.add_layer(
+        pattern.add_layer(
             "prim.sub",
             inputs={"x": gen_name(9)},
             outputs=[gen_name(10)],
             y=2)
-            self.pattern.add_layer(
+        pattern.add_layer(
             "prim.list", inputs={}, outputs=[gen_name(11)])
-            self.pattern.add_layer(
+        pattern.add_layer(
             "prim.loop",
             inputs={"input": gen_name(10)},
             outputs=[gen_name(12.1), gen_name(12.2)])
-            loop_layer = self.pattern.layers[list(self.pattern.layers.keys())[
+        loop_layer = pattern.layers[list(pattern.layers.keys())[
             -1]]
         pattern_block = PaddleGraph(loop_layer, graph_type="dygraph")
         pattern_block.add_layer(
@@ -102,7 +96,7 @@ class DygraphInterpolateBilinearFuser(FuseBase):
             element=None)
         loop_layer.inputs["input-0"] = gen_name(11)
         loop_layer.add_block(pattern_block)
-            self.pattern.add_layer(
+        pattern.add_layer(
             "prim.tuple",
             inputs={
                 "input0": "interpolate-input-0",
@@ -112,17 +106,17 @@ class DygraphInterpolateBilinearFuser(FuseBase):
             input2=None,
             input3=None)
 
-            self.pattern.add_layer(
+        pattern.add_layer(
             "prim.eq",
             inputs={"x": "interpolate-input-2"},
             outputs=[gen_name(10.1)],
             y=3)
 
-            self.pattern.add_layer(
+        pattern.add_layer(
             "prim.if",
             inputs={"input": gen_name(10.1)},
             outputs=[gen_name(14)])
-            if_layer1 = self.pattern.layers[list(self.pattern.layers.keys())[
+        if_layer1 = pattern.layers[list(pattern.layers.keys())[
             -1]]
         pattern_block = PaddleGraph(parent_layer=if_layer1, graph_type="dygraph")
         pattern_block.add_layer(
@@ -259,14 +253,14 @@ class DygraphInterpolateBilinearFuser(FuseBase):
             'input-9': 'interpolate-input-3', 
             'input-10': 'interpolate-input-0'
         })
-            self.pattern.build(inputs={
+        pattern.build(inputs={
             "input-0": "interpolate-input-0",
             "input-1": "interpolate-input-1",
             "input-2": "interpolate-input-2",
             "input-3": "interpolate-input-3",
             "input-4": "interpolate-input-4"
         })
-            
+        self.patterns.append(pattern)