Merge pull request #906 from wjj19950828/support_GFPGAN

Support GFPGAN

docs/inference_model_convertor/op_list.md

@@ -117,7 +117,8 @@ Aten:
 | 125 | aten::complex | 126 | aten::real | 127 | aten::imag | 128 | aten::fft\_rfftn |
 | 129 | aten::fft\_irfftn | 130 | aten::hardsigmoid | 131 | aten::hardswish | 132 | aten::linear |
 | 133 | aten::rsqrt | 134 | aten::replication\_pad1d | 135 | aten::full | 136 | aten::group\_norm |
-| 137 | aten::argmax | 138 | aten::copy | 139 | aten::upsample\_trilinear3d |  |  |
+| 137 | aten::argmax | 138 | aten::copy | 139 | aten::upsample\_trilinear3d | 140 | aten::clone |
+| 141 | aten::rand | 142 | aten::randn |  |  |  |  |
 
 Prim:
 | 序号 | OP | 序号 | OP | 序号 | OP | 序号 | OP |

x2paddle/op_mapper/pytorch2paddle/aten.py

@@ -1087,6 +1087,36 @@ def aten_clamp_min(mapper, graph, node):
     return current_inputs, current_outputs
 
 
+def aten_clone(mapper, graph, node):
+    """
+    TorchScript Code:
+        %55 : Tensor = aten::clone(%54)
+        Parameter meaning:
+        %55 (Tensor): output tensor
+        %54 (Tensor): input tensor
+    """
+    scope_name = mapper.normalize_scope_name(node)
+    output_name = mapper._get_outputs_name(node)[0]
+    layer_outputs = [output_name]
+    layer_inputs = {}
+    inputs_name, inputs_node = mapper._get_inputs_name(node)
+    # outputs list
+    current_outputs = [output_name]
+    # inputs list
+    mapper._check_input(graph, inputs_node[0], inputs_name[0], current_outputs,
+                        scope_name)
+    layer_inputs["x"] = inputs_name[0]
+
+    current_inputs = list(layer_inputs.values())
+
+    graph.add_layer(
+        "paddle.clone",
+        inputs=layer_inputs,
+        outputs=layer_outputs,
+        scope_name=scope_name)
+    return current_inputs, current_outputs
+
+
 def aten_complex(mapper, graph, node):
     """
     TorchScript示例:
@@ -1347,23 +1377,102 @@ def aten_conv2d(mapper, graph, node):
 
 
 def aten__convolution(mapper, graph, node):
-    """ 构造conv2d的PaddleLayer。
-    TorchScript示例:
+    """
+    TorchScript Code:
         %input.10 : Tensor = aten::_convolution(%input.1, %18, %10, %19, %20, %21, %13, %22, %12, %13, %13, %15)
-        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 (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。
+        Parameter meaning:
+        %input.10 (Tensor): Output Tensor
+        %input.8 (Tensor): Input Tensor
+        %18 (Tensor): weights
+        %10 (Tensor): bias
+        %19 (list): stride
+        %20 (list): padding
+        %21 (list): dilation
+        %13 (bool): whether transpose
+        %22 (list): output_padding
+        %12 (int): groups
     """
     scope_name = mapper.normalize_scope_name(node)
     inputs_name, inputs_node = mapper._get_inputs_name(node)
+    layer_attrs = {}
+    # deal with stride
+    layer_attrs["stride"] = mapper.attrs[inputs_name[3]]
+    # deal with padding
+    layer_attrs["padding"] = mapper.attrs[inputs_name[4]]
+    # deal with dilation
+    layer_attrs["dilation"] = mapper.attrs[inputs_name[5]]
+    # deal with groups
+    layer_attrs["groups"] = mapper.attrs[inputs_name[8]]
+    # for weight is nn.functional.conv2d input
+    if inputs_name[1] not in mapper.pytorch_params:
+        output_name = mapper._get_outputs_name(node)[0]
+        layer_outputs = [output_name]
+        layer_inputs = {}
+        current_outputs = [output_name]
+        # input
+        mapper._check_input(graph, inputs_node[0], inputs_name[0],
+                            current_outputs, scope_name)
+        layer_inputs["x"] = inputs_name[0]
+        # weight
+        mapper._check_input(graph, inputs_node[1], inputs_name[1],
+                            current_outputs, scope_name)
+        layer_inputs["weight"] = inputs_name[1]
+        layer_attrs["bias"] = mapper.attrs[inputs_name[2]]
+        current_inputs = list(layer_inputs.values())
+        # Determine whether it is conv or convtranspose according to the attribute
+        if len(layer_attrs["stride"]) == 1:
+            if mapper.attrs[inputs_name[6]]:
+                # only convtranspose have output_padding attr
+                layer_attrs["output_padding"] = mapper.attrs[inputs_name[7]]
+                graph.add_layer(
+                    "paddle.nn.functional.conv1d_transpose",
+                    inputs=layer_inputs,
+                    outputs=layer_outputs,
+                    scope_name=scope_name,
+                    **layer_attrs)
+            else:
+                graph.add_layer(
+                    "paddle.nn.functional.conv1d",
+                    inputs=layer_inputs,
+                    outputs=layer_outputs,
+                    scope_name=scope_name,
+                    **layer_attrs)
+        elif len(layer_attrs["stride"]) == 2:
+            if mapper.attrs[inputs_name[6]]:
+                # only convtranspose have output_padding attr
+                layer_attrs["output_padding"] = mapper.attrs[inputs_name[7]]
+                graph.add_layer(
+                    "paddle.nn.functional.conv2d_transpose",
+                    inputs=layer_inputs,
+                    outputs=layer_outputs,
+                    scope_name=scope_name,
+                    **layer_attrs)
+            else:
+                graph.add_layer(
+                    "paddle.nn.functional.conv2d",
+                    inputs=layer_inputs,
+                    outputs=layer_outputs,
+                    scope_name=scope_name,
+                    **layer_attrs)
+        elif len(layer_attrs["stride"]) == 3:
+            if mapper.attrs[inputs_name[6]]:
+                # only convtranspose have output_padding attr
+                layer_attrs["output_padding"] = mapper.attrs[inputs_name[7]]
+                graph.add_layer(
+                    "paddle.nn.functional.conv3d_transpose",
+                    inputs=layer_inputs,
+                    outputs=layer_outputs,
+                    scope_name=scope_name,
+                    **layer_attrs)
+            else:
+                graph.add_layer(
+                    "paddle.nn.functional.conv3d",
+                    inputs=layer_inputs,
+                    outputs=layer_outputs,
+                    scope_name=scope_name,
+                    **layer_attrs)
+        return current_inputs, current_outputs
+    else:
         weights = mapper.pytorch_params[inputs_name[1]]
         if len(weights.shape) == 3:
             op_name = name_generator("conv1d", mapper.nn_name2id)
@@ -1374,16 +1483,11 @@ def aten__convolution(mapper, graph, node):
         output_name = mapper._get_outputs_name(node)[0]
         layer_outputs = [op_name, output_name]
         layer_inputs = {}
-    layer_attrs = {}
-    # 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)
+        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
         mapper.paddle_params[op_name +
                              ".weight"] = weights  #np.swapaxes(weights, 0, 1)
         if mapper.attrs[inputs_name[6]]:
@@ -1391,7 +1495,7 @@ def aten__convolution(mapper, graph, node):
         else:
             layer_attrs["out_channels"] = weights.shape[0]
         layer_attrs["kernel_size"] = weights.shape[2:]
-    # 处理输入2，即%10
+        # deal with bias
         if inputs_name[2] in mapper.pytorch_params:
             bias = mapper.pytorch_params[inputs_name[2]]
             if bias is not None:
@@ -1400,18 +1504,6 @@ def aten__convolution(mapper, graph, node):
                 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["dilation"] = mapper.attrs[inputs_name[5]]
-    # 处理输入6，即%13
-    if mapper.attrs[inputs_name[6]]:
-        # 处理输入7，即%22
-        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]]
@@ -1420,6 +1512,8 @@ def aten__convolution(mapper, graph, node):
                 inputs_name[8]]
         if len(weights.shape) == 3:
             if mapper.attrs[inputs_name[6]]:
+                # only convtranspose have output_padding attr
+                layer_attrs["output_padding"] = mapper.attrs[inputs_name[7]]
                 graph.add_layer(
                     "paddle.nn.Conv1DTranspose",
                     inputs=layer_inputs,
@@ -1435,6 +1529,8 @@ def aten__convolution(mapper, graph, node):
                     **layer_attrs)
         elif len(weights.shape) == 4:
             if mapper.attrs[inputs_name[6]]:
+                # only convtranspose have output_padding attr
+                layer_attrs["output_padding"] = mapper.attrs[inputs_name[7]]
                 graph.add_layer(
                     "paddle.nn.Conv2DTranspose",
                     inputs=layer_inputs,
@@ -1450,6 +1546,8 @@ def aten__convolution(mapper, graph, node):
                     **layer_attrs)
         else:
             if mapper.attrs[inputs_name[6]]:
+                # only convtranspose have output_padding attr
+                layer_attrs["output_padding"] = mapper.attrs[inputs_name[7]]
                 graph.add_layer(
                     "paddle.nn.Conv3DTranspose",
                     inputs=layer_inputs,
@@ -4385,6 +4483,88 @@ def aten_prelu(mapper, graph, node):
     return current_inputs, current_outputs
 
 
+def aten_rand(mapper, graph, node):
+    """
+    TorchScript Code:
+        %input.49 : Tensor = aten::rand(%23, %8, %6, %24, %5)
+        Parameter meaning:
+        %input.49 (Tensor): output tensor
+        %23 (list): input shape list
+        %8 (int): dtype。
+        %6 (int): layout。
+        %4995 (int): device
+        %4995 (bool): requires_grad
+    """
+    scope_name = mapper.normalize_scope_name(node)
+    output_name = mapper._get_outputs_name(node)[0]
+    layer_outputs = [output_name]
+    layer_inputs = {}
+    layer_attrs = {}
+    inputs_name, inputs_node = mapper._get_inputs_name(node)
+    # outputs list
+    current_outputs = [output_name]
+    current_inputs = []
+    # deal with shape
+    if inputs_name[0] in mapper.attrs:
+        layer_attrs["shape"] = mapper.attrs[inputs_name[0]]
+    else:
+        mapper._check_input(graph, inputs_node[0], inputs_name[0],
+                            current_outputs, scope_name)
+        layer_inputs["shape"] = inputs_name[0]
+        current_inputs.append(inputs_name[0])
+    # deal with dtype
+    layer_attrs["dtype"] = dtype_dict[mapper.attrs[inputs_name[1]]]
+
+    graph.add_layer(
+        "paddle.rand",
+        inputs=layer_inputs,
+        outputs=layer_outputs,
+        scope_name=scope_name,
+        **layer_attrs)
+    return current_inputs, current_outputs
+
+
+def aten_randn(mapper, graph, node):
+    """
+    TorchScript Code:
+        %input.49 : Tensor = aten::randn(%23, %8, %6, %24, %5)
+        Parameter meaning:
+        %input.49 (Tensor): output tensor
+        %23 (list): input shape list
+        %8 (int): dtype。
+        %6 (int): layout。
+        %4995 (int): device
+        %4995 (bool): requires_grad
+    """
+    scope_name = mapper.normalize_scope_name(node)
+    output_name = mapper._get_outputs_name(node)[0]
+    layer_outputs = [output_name]
+    layer_inputs = {}
+    layer_attrs = {}
+    inputs_name, inputs_node = mapper._get_inputs_name(node)
+    # outputs list
+    current_outputs = [output_name]
+    current_inputs = []
+    # deal with shape
+    if inputs_name[0] in mapper.attrs:
+        layer_attrs["shape"] = mapper.attrs[inputs_name[0]]
+    else:
+        mapper._check_input(graph, inputs_node[0], inputs_name[0],
+                            current_outputs, scope_name)
+        layer_inputs["shape"] = inputs_name[0]
+        current_inputs.append(inputs_name[0])
+    # deal with dtype
+    layer_attrs["dtype"] = dtype_dict[mapper.attrs[inputs_name[1]]]
+
+    graph.add_layer(
+        "paddle.randn",
+        inputs=layer_inputs,
+        outputs=layer_outputs,
+        scope_name=scope_name,
+        **layer_attrs)
+    return current_inputs, current_outputs
+
+
 def aten_real(mapper, graph, node):
     """
     TorchScript示例: