Merge pull request #3 from PaddlePaddle/develop

Develop

Q&A.md

+## 常见问题
+
+**Q1. TensorFlow模型转换过程中，提示『Unknown shape for input tensor[tensor name: "input"]， Please define shape of input here』？**  
+A：该提示信息表示无法从TensorFlow的pb模型中获取到输入tensor(tensor名为"input:)的shape信息，所以需要用户手动在提示后输入详细的shape信息，如None,224,224,3 其中None表示Batch 

README.md

@@ -33,4 +33,4 @@ x2paddle --framework=caffe --proto=deploy.proto --weight=deploy.caffemodel --sav
 
 ## Related Docs
 1. [X2Paddle使用过程中常见问题](Q&A.md)  
-2. [如何导出TensorFlow的pb模型](export_tf_model.md)
+2. [如何导出TensorFlow的pb模型](export_tf_model.md)
\ No newline at end of file

x2paddle/convert.py

@@ -23,11 +23,11 @@ def arg_parser():
                         type=_text_type,
                         default=None,
                         help="model file path")
-    parser.add_argument("--proto",
+    parser.add_argument("--prototxt",
                         "-p",
                         type=_text_type,
                         default=None,
-                        help="proto file of caffe model")
+                        help="prototxt file of caffe model")
     parser.add_argument("--weight",
                         "-w",
                         type=_text_type,
@@ -43,6 +43,11 @@ def arg_parser():
                         type=_text_type,
                         default=None,
                         help="define which deeplearning framework")
+    parser.add_argument("--caffe_proto",
+                        "-c",
+                        type=_text_type,
+                        default=None,
+                        help="caffe proto file of caffe model")
     return parser
 
 
@@ -57,12 +62,12 @@ def tf2paddle(model_path, save_dir):
     mapper.save_python_model(save_dir)
 
 
-def caffe2paddle(proto, weight, save_dir):
+def caffe2paddle(proto, weight, save_dir, caffe_proto):
     from x2paddle.decoder.caffe_decoder import CaffeDecoder
     from x2paddle.op_mapper.caffe_op_mapper import CaffeOpMapper
 
     print("Now translating model from caffe to paddle.")
-    model = CaffeDecoder(proto, weight)
+    model = CaffeDecoder(proto, weight, caffe_proto)
     mapper = CaffeOpMapper(model)
     mapper.run()
     mapper.save_python_model(save_dir)
@@ -80,8 +85,9 @@ def main():
         tf2paddle(args.model, args.save_dir)
 
     elif args.framework == "caffe":
-        assert args.proto is not None, "--proto and --weight should be defined while translating caffe model"
-        caffe2paddle(args.proto, args.weight, args.save_dir)
+        assert args.prototxt is not None and args.weight is not None, "--prototxt and --weight should be defined while translating caffe model"
+        caffe2paddle(args.prototxt, args.weight, args.save_dir,
+                     args.caffe_proto)
 
     else:
         raise Exception("--framework only support tensorflow/caffe now")

x2paddle/core/fluid_code.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 from x2paddle.core.graph import GraphNode
-import collections
 
 
 class Layer(object):
@@ -22,6 +21,7 @@ class Layer(object):
         self.param_attr = dict()
         self.inputs = dict()
         self.output = None
+        self.is_new = False
 
     def get_code(self):
         layer_code = ""
@@ -36,34 +36,25 @@ class Layer(object):
         if isinstance(self.inputs, list):
             in_list = "["
             for input in self.inputs:
-                if isinstance(input, GraphNode):
-                    if hasattr(input, "index"):
-                        in_list += (input.layer_name +
-                                    "[{}]".format(input.index) + ", ")
-                    else:
-                        in_list += (input.layer_name + ", ")
-                elif isinstance(input, str):
-                    in_list += (input + ", ")
+                assert isinstance(
+                    input, GraphNode), "Type of input should be GraphNode"
+                if hasattr(input, "index"):
+                    in_list += (input.layer_name + "[{}]".format(input.index) +
+                                ", ")
                 else:
-                    raise Exception(
-                        "Element of inputs should GraphNode or String")
+                    in_list += (input.layer_name + ", ")
             in_list = in_list.strip(", ") + "], "
             layer_code += in_list
         elif isinstance(self.inputs, dict):
-            inputs = collections.OrderedDict(self.inputs)
-            for key, input in inputs.items():
-                if isinstance(input, GraphNode):
-                    if hasattr(input, "index"):
-                        layer_code = layer_code + key + "={}, ".format(
-                            input.layer_name + "[{}]".format(input.index))
-                    else:
-                        layer_code = layer_code + key + "={}, ".format(
-                            input.layer_name)
-                elif isinstance(input, str):
-                    layer_code = layer_code + key + "={}, ".format(input)
+            for key, input in self.inputs.items():
+                assert isinstance(
+                    input, GraphNode), "Type of input should be GraphNode"
+                if hasattr(input, "index"):
+                    layer_code = layer_code + key + "={}, ".format(
+                        input.layer_name + "[{}]".format(input.index))
                 else:
-                    raise Exception(
-                        "Element of inputs should GraphNode or String")
+                    layer_code = layer_code + key + "={}, ".format(
+                        input.layer_name)
         elif isinstance(self.inputs, GraphNode):
             if hasattr(self.inputs, "index"):
                 layer_code += (self.inputs.layer_name +
@@ -75,8 +66,38 @@ class Layer(object):
         else:
             raise Exception("Unknown type of inputs.")
 
-        param_attr = collections.OrderedDict(self.param_attr)
-        for key, value in param_attr.items():
+        for key, value in self.param_attr.items():
+            layer_code = layer_code + key + "={}, ".format(value)
+        layer_code = layer_code.strip(", ")
+
+        return layer_code + ")"
+
+    def get_custom_code(self):
+        layer_code = ""
+        if self.output is not None:
+            if isinstance(self.output, str):
+                layer_code = self.output + " = "
+            else:
+                layer_code = self.output.layer_name + " = "
+
+        layer_code = layer_code + self.op + "("
+
+        if isinstance(self.inputs, list):
+            in_list = "["
+            for input in self.inputs:
+                assert isinstance(
+                    input, GraphNode), "Type of input should be GraphNode"
+                if hasattr(input, "index"):
+                    in_list += (input.layer_name + "[{}]".format(input.index) +
+                                ", ")
+                else:
+                    in_list += (input.layer_name + ", ")
+            in_list = in_list.strip(", ") + "], "
+            layer_code += in_list
+        else:
+            raise Exception("Unknown type of inputs.")
+
+        for key, value in self.param_attr.items():
             layer_code = layer_code + key + "={}, ".format(value)
         layer_code = layer_code.strip(", ")
 
@@ -87,9 +108,15 @@ class FluidCode(object):
     def __init__(self):
         self.layers = list()
 
-    def add_layer(self, op, inputs, output, param_attr=None):
+    def add_layer(self,
+                  op,
+                  inputs,
+                  output,
+                  param_attr=None,
+                  is_custom_layer=False):
         layer = Layer()
         layer.op = op
+        layer.is_custom_layer = is_custom_layer
         if inputs is not None:
             layer.inputs = inputs
         layer.output = output
@@ -108,7 +135,10 @@ class FluidCode(object):
         codes = list()
         for layer in self.layers:
             if isinstance(layer, Layer):
-                codes.append(layer.get_code())
+                if layer.is_custom_layer:
+                    codes.append(layer.get_custom_code())
+                else:
+                    codes.append(layer.get_code())
             elif isinstance(layer, str):
                 codes.append(layer)
         return codes

x2paddle/decoder/caffe_decoder.py

@@ -18,19 +18,20 @@ from google.protobuf import text_format
 import numpy as np
 from x2paddle.core.graph import GraphNode, Graph
 from x2paddle.core.fluid_code import FluidCode
-from x2paddle.decoder import caffe_shape
+from x2paddle.op_mapper import caffe_shape
 
 
 class CaffeResolver(object):
-    def __init__(self, use_default=True):
-        self.use_default = use_default
+    def __init__(self, caffe_proto_folder=None):
+        self.proto_path = caffe_proto_folder
+        if self.proto_path == None:
+            self.use_default = True
+        else:
+            self.use_default = False
         self.import_caffe()
 
     def import_caffepb(self):
-        p = os.path.realpath(__file__)
-        p = os.path.dirname(p)
-        p = os.path.join(p, './proto')
-        sys.path.insert(0, p)
+        sys.path.append(self.proto_path)
         import caffe_pb2
         return caffe_pb2
 
@@ -60,11 +61,13 @@ class CaffeResolver(object):
 class CaffeGraphNode(GraphNode):
     def __init__(self, layer, layer_name=None):
         if layer_name is None:
-            super(CaffeGraphNode, self).__init__(layer,
-                                                 layer.name.replace('/', '_'))
+            super(CaffeGraphNode,
+                  self).__init__(layer,
+                                 layer.name.replace('/', '_').replace('-', '_'))
         else:
-            super(CaffeGraphNode, self).__init__(layer,
-                                                 layer_name.replace('/', '_'))
+            super(CaffeGraphNode,
+                  self).__init__(layer,
+                                 layer_name.replace('/', '_').replace('-', '_'))
         self.layer_type = layer.type
         self.fluid_code = FluidCode()
         self.data = None
@@ -72,10 +75,13 @@ class CaffeGraphNode(GraphNode):
     def set_params(self, params):
         self.data = params
 
-    def set_output_shape(self, input_shape):
+    def set_output_shape(self, input_shape, is_input=True):
         func_name = 'shape_' + self.layer_type.lower()
-        self.output_shape = getattr(caffe_shape, func_name)(self.layer,
-                                                            input_shape)
+        if is_input:
+            self.output_shape = getattr(caffe_shape, func_name)(self.layer,
+                                                                input_shape)
+        else:
+            self.output_shape = input_shape
 
     def set_input_shape(self, input_shape):
         self.input_shape = input_shape
@@ -135,7 +141,7 @@ class CaffeGraph(Graph):
                                      ]))).to_proto().layer[0])
                     except:
                         raise ImportError(
-                            'You must install the caffe first when you use old style prototxt.'
+                            'The .proto file does not work for the old style prototxt. You must install the caffe or modify the old style to new style in .protottx file.'
                         )
                     data.name = self.model.input[i]
                     data.top[0] = self.model.input[i]
@@ -151,7 +157,7 @@ class CaffeGraph(Graph):
                                      ]))).to_proto().layer[0])
                     except:
                         raise ImportError(
-                            'You must install the caffe first when you use old style prototxt.'
+                            'The .proto file does not work for the old style prototxt. You must install the caffe or modify the old style to new style in .protottx file.'
                         )
                     data.name = self.model.input[i]
                     data.top[0] = self.model.input[i]
@@ -180,19 +186,6 @@ class CaffeGraph(Graph):
             else:
                 notice('Ignoring parameters for non-existent layer: %s' % \
                         layer_name)
-        for layer_name in self.node_map:
-            node = self.node_map[layer_name]
-            inputs = node.inputs
-            i = 0
-            input_shape = []
-            for nm in inputs:
-                last_node = self.get_node(nm)
-                tmp = node.layer.bottom[i]
-                i = i + 1
-                idx = list(last_node.layer.top).index(tmp)
-                input_shape.append(last_node.output_shape[idx])
-            node.set_output_shape(input_shape)
-            node.set_input_shape(input_shape)
 
         super(CaffeGraph, self).build()
 
@@ -210,11 +203,11 @@ class CaffeGraph(Graph):
 
 
 class CaffeDecoder(object):
-    def __init__(self, proto_path, model_path, use_caffe=True):
+    def __init__(self, proto_path, model_path, caffe_proto_folder=None):
         self.proto_path = proto_path
         self.model_path = model_path
 
-        self.resolver = CaffeResolver(use_default=use_caffe)
+        self.resolver = CaffeResolver(caffe_proto_folder=caffe_proto_folder)
         self.net = self.resolver.NetParameter()
         with open(proto_path, 'rb') as proto_file:
             proto_str = proto_file.read()

x2paddle/op_mapper/caffe_custom_layer/__init__.py

+from .register import get_registered_layers
+
+#custom layer import begins
+# from . import roipooling
+# from . import priorbox
+# from . import permute
+# from . import detection_out
+# from . import normalize
+# from . import select
+from . import convolutiondepthwise
+#custom layer import ends
+
+custom_layers = get_registered_layers()
+
+
+def set_args(f, params):
+    """ set args for function 'f' using the parameters in node.layer.param
+    Args:
+        f (function): a python function object
+        params (object): a object contains attributes needed by f's arguments
+    Returns:
+        arg_names (list): a list of argument names
+        kwargs (dict): a dict contains needed arguments
+    """
+    argc = f.__code__.co_argcount
+    arg_list = f.__code__.co_varnames[0:argc]
+    kwargs = {}
+    for arg_name in arg_list:
+        if hasattr(params, arg_name) and params is not None:
+            kwargs[arg_name] = getattr(params, arg_name)
+    return arg_list, kwargs
+
+
+def has_layer(layer_type):
+    """ test whether this layer exists in custom layer
+    """
+    return layer_type in custom_layers
+
+
+def get_params(layer, layer_type):
+    if layer_type.lower() == "deconvolution" or layer_type.lower(
+    ) == "convolutiondepthwise":
+        param_name = '_'.join(('convolution', 'param'))
+    elif layer_type.lower() == "normalize":
+        param_name = '_'.join(('norm', 'param'))
+    else:
+        param_name = '_'.join((layer_type.lower(), 'param'))
+    return getattr(layer, param_name, None)
+
+
+def compute_output_shape(node):
+    """ compute the output shape of custom layer
+    """
+    layer_type = node.layer_type
+    assert layer_type in custom_layers, "layer[%s] not exist in custom layers" % (
+        layer_type)
+    shape_func = custom_layers[layer_type]['shape']
+    layer = node.layer
+    params = get_params(layer, layer_type)
+    arg_names, kwargs = set_args(shape_func, params)
+    input_shape = node.input_shape
+    return shape_func(input_shape, **kwargs)
+
+
+def make_custom_layer(node):
+    """ get the code which implement the custom layer function
+    """
+    layer_type = node.layer_type
+    assert layer_type in custom_layers, "layer[%s] not exist in custom layers" % (
+        layer_type)
+    layer_func = custom_layers[layer_type]['layer']
+    import inspect
+    return inspect.getsource(layer_func), layer_func
+
+
+def deal_weights(node, data=None):
+    """ deal the weights of the custom layer
+    """
+    layer_type = node.layer_type
+    weights_func = custom_layers[layer_type]['weights']
+    name = node.layer_name
+    return weights_func(name, data)

x2paddle/op_mapper/caffe_custom_layer/convolutiondepthwise.py

+from .register import register
+from x2paddle.core.util import *
+import numbers
+
+
+def convolutiondepthwise_shape(input_shape,
+                               num_output=None,
+                               pad=None,
+                               kernel_size=None,
+                               stride=None,
+                               dilation=None,
+                               pad_h=None,
+                               pad_w=None,
+                               kernel_h=None,
+                               kernel_w=None,
+                               stride_h=None,
+                               stride_w=None):
+    [k_h, k_w] = [1, 1]
+    if isinstance(kernel_size, numbers.Number):
+        [k_h, k_w] = [kernel_size] * 2
+    elif isinstance(kernel_size, list):
+        k_h = kernel_h if kernel_h else kernel_size[0]
+        k_w = kernel_w if kernel_w else kernel_size[len(kernel_size) - 1]
+    [s_h, s_w] = [1, 1]
+    if isinstance(stride, numbers.Number):
+        [s_h, s_w] = [stride] * 2
+    elif isinstance(stride, list):
+        s_h = stride_h if stride_h else stride[0]
+        s_w = stride_w if stride_w else stride[len(stride) - 1]
+    [p_h, p_w] = [0, 0]
+    if isinstance(pad, numbers.Number):
+        [p_h, p_w] = [pad] * 2
+    elif isinstance(pad, list):
+        p_h = pad_h if pad_h else pad[0]
+        p_w = pad_w if pad_w else pad[len(pad) - 1]
+    dila_len = len(dilation)
+    dila_h = 1
+    dila_w = 1
+    if dila_len == 2:
+        dila_h = dilation[0]
+        dila_w = dilation[1]
+    elif dila_len == 1:
+        dila_h = dila_w = dilation[0]
+    else:
+        assert dila_len == 0, "invalid length[%s] of dilation in convolution" % (
+            dila_len)
+    i_w = input_shape[0][2]
+    i_h = input_shape[0][3]
+    o_h = (i_h + 2 * p_h - (dila_h * (k_h - 1) + 1)) / float(s_h) + 1
+    o_w = (i_w + 2 * p_w - (dila_w * (k_w - 1) + 1)) / float(s_w) + 1
+    import math
+    o_h = int(math.floor(o_h))
+    o_w = int(math.floor(o_w))
+    c = num_output if num_output is not None else input_shape[0][1]
+    return [[input_shape[0][0], c, o_h, o_w]]
+
+
+def convolutiondepthwise_layer(inputs,
+                               num_output=None,
+                               pad=None,
+                               kernel_size=None,
+                               stride=None,
+                               dilation=None,
+                               pad_h=None,
+                               pad_w=None,
+                               kernel_h=None,
+                               kernel_w=None,
+                               stride_h=None,
+                               stride_w=None,
+                               input_shape=[],
+                               name=None):
+    [k_h, k_w] = [1, 1]
+    if isinstance(kernel_size, numbers.Number):
+        [k_h, k_w] = [kernel_size] * 2
+    elif isinstance(kernel_size, list):
+        k_h = kernel_h if kernel_h else kernel_size[0]
+        k_w = kernel_w if kernel_w else kernel_size[len(kernel_size) - 1]
+    [s_h, s_w] = [1, 1]
+    if isinstance(stride, numbers.Number):
+        [s_h, s_w] = [stride] * 2
+    elif isinstance(stride, list):
+        s_h = stride_h if stride_h else stride[0]
+        s_w = stride_w if stride_w else stride[len(stride) - 1]
+    [p_h, p_w] = [0, 0]
+    if isinstance(pad, numbers.Number):
+        [p_h, p_w] = [pad] * 2
+    elif isinstance(pad, list):
+        p_h = pad_h if pad_h else pad[0]
+        p_w = pad_w if pad_w else pad[len(pad) - 1]
+    input = inputs[0]
+    dila_len = len(dilation)
+    dila_h = 1
+    dila_w = 1
+    if dila_len == 2:
+        dila_h = dilation[0]
+        dila_w = dilation[1]
+    elif dila_len == 1:
+        dila_h = dila_w = dilation[0]
+    else:
+        assert dila_len == 0, "invalid length[%s] of dilation in convolution" % (
+            dila_len)
+    c_in = input_shape[0][1]
+    c_out = num_output if num_output is not None else input_shape[0][1]
+    group = int(c_in / (c_in / c_out)) if c_in > c_out else int(c_in /
+                                                                (c_out / c_in))
+    out = fluid.layers.conv2d(input,
+                              dilation=[dila_h, dila_w],
+                              filter_size=[k_h, k_w],
+                              stride=[s_h, s_w],
+                              padding=[p_h, p_w],
+                              groups=group,
+                              num_filters=c_out,
+                              param_attr=name + '_weights',
+                              bias_attr=name + '_bias',
+                              name=name)
+    return out
+
+
+def convolutiondepthwise_weights(name, data=None):
+    weights_name = []
+    weights_name.append(name + '_weights')
+    weights_name.append(name + '_bias')
+    return weights_name
+
+
+register(kind='ConvolutionDepthwise',
+         shape=convolutiondepthwise_shape,
+         layer=convolutiondepthwise_layer,
+         weights=convolutiondepthwise_weights)

x2paddle/op_mapper/caffe_custom_layer/register.py

+""" this module provides 'register' for registering customized layers
+"""
+
+g_custom_layers = {}
+
+
+def register(kind, shape, layer, weights):
+    """ register a custom layer or a list of custom layers
+
+    Args:
+        @kind (str or list): type name of the layer
+        @shape (function): a function to generate the shape of layer's output
+        @layer (function): a function to generate the paddle code of layer
+        @weights (function): a function to deal with weights data
+
+    Returns:
+        None
+    """
+    assert type(shape).__name__ == 'function', 'shape should be a function'
+    assert type(layer).__name__ == 'function', 'layer should be a function'
+
+    if type(kind) is str:
+        kind = [kind]
+    else:
+        assert type(
+            kind
+        ) is list, 'invalid param "kind" for register, not a list or str'
+
+    for k in kind:
+        assert type(
+            k) is str, 'invalid param "kind" for register, not a list of str'
+        assert k not in g_custom_layers, 'this type[%s] has already been registered' % (
+            k)
+        print('register layer[%s]' % (k))
+        g_custom_layers[k] = {
+            'shape': shape,
+            'layer': layer,
+            'weights': weights
+        }
+
+
+def get_registered_layers():
+    return g_custom_layers

x2paddle/op_mapper/caffe_op_mapper.py

@@ -17,6 +17,7 @@ import numpy as np
 from x2paddle.decoder.caffe_decoder import CaffeGraph
 from x2paddle.core.op_mapper import OpMapper
 from x2paddle.core.util import *
+from x2paddle.op_mapper.caffe_custom_layer import *
 
 
 class CaffeOpMapper(OpMapper):
@@ -25,34 +26,72 @@ class CaffeOpMapper(OpMapper):
         self.graph = decoder.caffe_graph
         self.weights = dict()
         resolver = decoder.resolver
+        self.mylayers = {}
         if resolver.has_pycaffe():
             self.did_use_pb = False
         else:
             self.did_use_pb = True
 
+    def op_checker(self):
+        unsupported_ops = set()
+        for node_name in self.graph.topo_sort:
+            node = self.graph.get_node(node_name)
+            op = node.layer_type
+            if not hasattr(self, op) and op not in custom_layers:
+                unsupported_ops.add(op)
+        if len(unsupported_ops) == 0:
+            return True
+        else:
+            print("There are {} ops not supported yet, list as below".format(
+                len(unsupported_ops)))
+            for op in unsupported_ops:
+                print(op)
+            return False
+
     def run(self):
         print("Total nodes: {}".format(len(self.graph.topo_sort)))
-
         # check if ops in model are all supported
         if not self.op_checker():
             raise Exception("Model are not supported yet.")
-
         for node_name in self.graph.topo_sort:
             node = self.graph.get_node(node_name)
             op = node.layer_type
             if hasattr(self, op):
+                self.set_shape(node)
                 func = getattr(self, op)
                 func(node)
+            elif op in custom_layers:
+                self.set_shape(node, is_fluid_op=False)
+                self.deal_custom_layer(node)
+            else:
+                raise Exception("Model are not supported yet.")
+        for key in self.mylayers:
+            self.net_code.append(self.mylayers[key])
 
         for i in range(len(self.graph.topo_sort)):
             node_name = self.graph.topo_sort[i]
             node = self.graph.get_node(node_name)
             self.net_code += node.fluid_code.gen_codes()
 
-    def adjust_parameters(self, node, data):
+    def set_shape(self, node, is_fluid_op=True):
+        inputs = node.inputs
+        input_shape = []
+        for i, nm in enumerate(inputs):
+            last_node = self.graph.get_node(nm)
+            tmp = node.layer.bottom[i]
+            idx = list(last_node.layer.top).index(tmp)
+            input_shape.append(last_node.output_shape[idx])
+        node.set_input_shape(input_shape)
+        if is_fluid_op:
+            node.set_output_shape(input_shape)
+        else:
+            node.set_output_shape(compute_output_shape(node),
+                                  is_input=is_fluid_op)
+
+    def adjust_parameters(self, node):
+        data = node.data
         if not self.did_use_pb:
             return data
-
         # When using the protobuf-backend, each parameter initially has four dimensions.
         # In certain cases (like FC layers), we want to eliminate the singleton dimensions.
         # This implementation takes care of the common cases. However, it does leave the
@@ -61,7 +100,7 @@ class CaffeOpMapper(OpMapper):
         data = list(data)
 
         squeeze_indices = [1]  # Squeeze biases.
-        if node.kind == NodeKind.InnerProduct:
+        if node.layer_type == 'InnerProduct':
             squeeze_indices.append(0)  # Squeeze FC.
 
         for idx in squeeze_indices:
@@ -85,55 +124,44 @@ class CaffeOpMapper(OpMapper):
 
             data[idx] = np.squeeze(d, axis=sq_axis)
             shape_new = data[idx].shape
+            print('shape-old' + str(shape_old))
+            print('shape-new' + str(shape_new))
             if len(shape_old) != shape_new:
-                debug('squeeze idx:%d, with kind:%s,name:%s' % \
-                        (idx, node.kind, node.name))
+                print('squeeze idx:%d, with kind:%s,name:%s' % \
+                        (idx, node.layer_type, node.layer.name))
         return data
 
-    @staticmethod
-    def get_kernel_value(scalar, repeated, idx, default=None):
-        if scalar:
-            return scalar
-        if repeated:
-            if isinstance(repeated, numbers.Number):
-                return repeated
-            if len(repeated) == 1:
-                # Same value applies to all spatial dimensions
-                return int(repeated[0])
-            assert idx < len(repeated)
-            # Extract the value for the given spatial dimension
-            return repeated[idx]
-        if default is None:
-            raise ValueError('Unable to determine kernel parameter!')
-        return default
-
     def get_kernel_parameters(self, kind, params):
-        assert kind in ['Convolution', 'Pooling', 'Deconvolution']
-
-        k_h = self.get_kernel_value(params.kernel_h,
-                                    params.kernel_size,
-                                    0,
-                                    default=1)
-        k_w = self.get_kernel_value(params.kernel_w,
-                                    params.kernel_size,
-                                    1,
-                                    default=1)
-        s_h = self.get_kernel_value(params.stride_h,
-                                    params.stride,
-                                    0,
-                                    default=1)
-        s_w = self.get_kernel_value(params.stride_w,
-                                    params.stride,
-                                    1,
-                                    default=1)
-        p_h = self.get_kernel_value(params.pad_h, params.pad, 0, default=0)
-        p_w = self.get_kernel_value(params.pad_w, params.pad, 1, default=0)
+        assert kind in [
+            'Convolution', 'Pooling', 'Deconvolution', 'ConvolutionDepthwise'
+        ]
+        [k_h, k_w] = [1, 1]
+        print(params.kernel_size)
+        if isinstance(params.kernel_size, numbers.Number):
+            [k_h, k_w] = [params.kernel_size] * 2
+        else:
+            k_h = params.kernel_h if params.kernel_h else params.kernel_size[0]
+            k_w = params.kernel_w if params.kernel_w else params.kernel_size[
+                len(params.kernel_size) - 1]
+        [s_h, s_w] = [1, 1]
+        if isinstance(params.stride, numbers.Number):
+            [s_h, s_w] = [params.stride] * 2
+        else:
+            s_h = params.stride_h if params.stride_h else params.stride[0]
+            s_w = params.stride_w if params.stride_w else params.stride[
+                len(params.stride) - 1]
+        [p_h, p_w] = [0, 0]
+        if isinstance(params.pad, numbers.Number):
+            [p_h, p_w] = [params.pad] * 2
+        else:
+            p_h = params.pad_h if params.pad_h else params.pad[0]
+            p_w = params.pad_w if params.pad_w else params.pad[len(params.pad) -
+                                                               1]
         dila_h = dila_w = 1
         group = 1
         c_o = 1
-        if kind in ['Convolution', 'Deconvolution']:
+        if kind in ['Convolution', 'Deconvolution', 'ConvolutionDepthwise']:
             c_o = params.num_output
-            group = params.group
             dila_len = len(params.dilation)
             if dila_len == 2:
                 dila_h = params.dilation[0]
@@ -143,12 +171,12 @@ class CaffeOpMapper(OpMapper):
             else:
                 assert dila_len == 0, "invalid length[%s] of dilation in convolution" % (
                     dila_len)
-
+        if kind in ['Convolution', 'Deconvolution']:
+            group = params.group
         kernel = [k_h, k_w]
         stride = [s_h, s_w]
         pad = [p_h, p_w]
         dilation = [dila_h, dila_w]
-
         return c_o, kernel, stride, pad, dilation, group
 
     def get_input_name(self, node):
@@ -180,7 +208,7 @@ class CaffeOpMapper(OpMapper):
         data = node.data
         assert data is not None, 'The parameter of {} (type is {}) is not set. You need to use python package of caffe to set the default value.'.format(
             node.layer_name, node.layer_type)
-        data = self.adjust_parameters(node, data)
+        data = self.adjust_parameters(node)
         self.weights[node.layer_name + '_weights'] = data[0]
         if len(data) == 2:
             self.weights[node.layer_name + '_bias'] = data[1]
@@ -224,7 +252,7 @@ class CaffeOpMapper(OpMapper):
         data = node.data
         assert data is not None, 'The parameter of {} (type is {}) is not set. You need to use python package of caffe to set the default value.'.format(
             node.layer_name, node.layer_type)
-        data = self.adjust_parameters(node, data)
+        data = self.adjust_parameters(node)
         self.weights[node.layer_name + '_weights'] = data[0]
         if len(data) == 2:
             self.weights[node.layer_name + '_bias'] = data[1]
@@ -343,7 +371,7 @@ class CaffeOpMapper(OpMapper):
         data = node.data
         assert data is not None, 'The parameter of {} (type is {}) is not set. You need to use python package of caffe to set the default value.'.format(
             node.layer_name, node.layer_type)
-        data = self.adjust_parameters(node, data)
+        data = self.adjust_parameters(node)
         # Reshape the parameters to Paddle's ordering
         transpose_order = (1, 0)
         w = data[0]
@@ -396,40 +424,11 @@ class CaffeOpMapper(OpMapper):
         shape = node.input_shape[0]
         dims = len(shape)
         axis = axis + dims if axis < 0 else axis
-        need_transpose = False
-        if axis + 1 != dims:
-            need_transpose = True
-        if need_transpose:
-            in_order = list(range(dims))
-            in_order.remove(axis)
-            in_order.append(axis)
-            attr = {
-                'perm': in_order,
-                'name': string(node.layer_name + '_transpose_in')
-            }
-            node.fluid_code.add_layer("transpose",
-                                      inputs=input,
-                                      output=node,
-                                      param_attr=attr)
-        attr = {'name': string(node.layer_name + '_softmax')}
+        attr = {'axis': axis, 'name': string(node.layer_name + '_softmax')}
         node.fluid_code.add_layer("softmax",
-                                  inputs=node if need_transpose else input,
+                                  inputs=input,
                                   output=node,
                                   param_attr=attr)
-        if need_transpose:
-            out_order = [
-                0,
-            ] * dims
-            for id, v in enumerate(in_order):
-                out_order[v] = id
-            attr = {
-                'perm': out_order,
-                'name': string(node.layer_name + '_transpose_out')
-            }
-            node.fluid_code.add_layer("transpose",
-                                      inputs=node,
-                                      output=node,
-                                      param_attr=attr)
 
     def Slice(self, node):
         assert len(
@@ -451,13 +450,11 @@ class CaffeOpMapper(OpMapper):
             attr = {
                 'axes': [axis],
                 'starts': [points[i]],
-                'ends': [points[i + 1]],
-                'name': string(node.layer_name + '_' + str(i))
+                'ends': [points[i + 1]]
             }
             node.fluid_code.add_layer("slice",
                                       inputs=input,
-                                      output=string(node.layer_name + '_' +
-                                                    str(i)),
+                                      output=node.layer_name + '_' + str(i),
                                       param_attr=attr)
             node.fluid_code.add_note('{}.append({})'.format(
                 node.layer_name, node.layer_name + '_' + str(i)))
@@ -503,7 +500,7 @@ class CaffeOpMapper(OpMapper):
             node.layer_name, node.layer_type)
         self.weights[node.layer_name + '_weights'] = data[0]
         attr = {
-            'mode': mode,
+            'mode': string(mode),
             'param_attr': string(node.layer_name + '_weights'),
             'name': string(node.layer_name)
         }
@@ -731,7 +728,7 @@ class CaffeOpMapper(OpMapper):
 
     def Scale(self, node):
         assert len(
-            node.outputs) == 1, 'The count of Scale node\'s output is not 1.'
+            node.inputs) == 1, 'The count of Scale node\'s input is not 1.'
         if len(node.inputs) == 1 and self.graph.get_node(
                 node.inputs[0]).layer_type == 'BatchNorm':
             return
@@ -1058,7 +1055,9 @@ class CaffeOpMapper(OpMapper):
                                   param_attr=attr)
         input_name = self.get_input_name(input)
         data = node.data
-        data = self.adjust_parameters(node, data)
+        assert data is not None, 'The parameter of {} (type is {}) is not set. You need to use python package of caffe to set the default value.'.format(
+            node.layer_name, node.layer_type)
+        data = self.adjust_parameters(node)
         self.weights[node.layer_name + '_scale'] = data[0]
         node.fluid_code.add_note(
             '{}_scale_attr = ParamAttr(name=\'{}\')'.format(
@@ -1297,7 +1296,7 @@ class CaffeOpMapper(OpMapper):
 
     def Select(self, node):
         assert len(
-            node.inputs) == 1, 'The count of Select node\'s input is not 2.'
+            node.inputs) == 1, 'The count of Select node\'s input is not 1.'
         input = self.graph.get_bottom_node(node, idx=0, copy=True)
         if self.is_Scale(input):
             tmp = self.graph.get_bottom_node(input, idx=0, copy=True)
@@ -1327,3 +1326,49 @@ class CaffeOpMapper(OpMapper):
                 node.layer_name, node.layer_name + '_' + str(i)))
             if i == len(slice_point) - 2:
                 break
+
+    def ShuffleChannel(self, node):
+        assert len(node.inputs
+                   ) == 1, 'The count of ShuffleChannel node\'s input is not 1.'
+        params = node.layer.shuffle_channel_param
+        group = params.group
+        input = self.graph.get_bottom_node(node, idx=0, copy=True)
+        if self.is_Scale(input):
+            tmp = self.graph.get_bottom_node(input, idx=0, copy=True)
+            if self.is_BN(tmp):
+                input = tmp
+        attr = {'group': group, 'name': string(node.layer_name)}
+        node.fluid_code.add_layer("shuffle_channel",
+                                  inputs=input,
+                                  output=node,
+                                  param_attr=attr)
+
+    def deal_custom_layer(self, node):
+        op = node.layer_type
+        custom_code, func = make_custom_layer(node)
+        params = get_params(node.layer, node.layer_type)
+        arg_names, kwargs = set_args(func, params)
+        kwargs['name'] = string(node.layer_name)
+        kwargs['input_shape'] = node.input_shape
+        data = node.data
+        assert data is not None, 'The parameter of {} (type is {}) is not set. You need to use python package of caffe to set the default value.'.format(
+            node.layer_name, node.layer_type)
+        data = self.adjust_parameters(node)
+        weights_name = deal_weights(node)
+        for i in range(len(data)):
+            self.weights[weights_name[i]] = data[i]
+        inputs_node = []
+        for i in range(len(node.inputs)):
+            input = self.graph.get_bottom_node(node, idx=i, copy=True)
+            if self.is_Scale(input):
+                tmp = self.graph.get_bottom_node(input, idx=0, copy=True)
+                if self.is_BN(tmp):
+                    input = tmp
+            inputs_node.append(input)
+        node.fluid_code.add_layer(func.__code__.co_name,
+                                  inputs=inputs_node,
+                                  output=node,
+                                  param_attr=kwargs,
+                                  is_custom_layer=True)
+        if op not in self.mylayers:
+            self.mylayers[op] = custom_code

x2paddle/decoder/caffe_shape.py → x2paddle/op_mapper/caffe_shape.py

@@ -453,3 +453,12 @@ def shape_select(layer, input_shape):
     output_shape = input_shape
     output_shape[axis] = end - start
     return [output_shape]
+
+
+def shape_shufflechannel(layer, input_shape):
+    return input_shape
+
+
+# def shape_convolutiondepthwise(layer, input_shape):
+#     params = layer.convolution_param
+#     return get_strided_kernel_output_shape(params, input_shape[0], math.floor)