Merge pull request #413 from PaddlePaddle/develop_0925

update tensorflow module

x2paddle/__init__.py

@@ -3,15 +3,3 @@ __version__ = "0.8.5"
 from .core.program import PaddleGraph
 
 program = PaddleGraph()
-
-name_counter = dict()
-
-
-def gen_name(op_name, var_name):
-    name = "{}.{}".format(op_name, var_name)
-    if name not in name_counter:
-        name_counter[name] = 0
-    else:
-        name_counter[name] += 1
-    name = name + "." + str(name_counter[name])
-    return name

x2paddle/convert.py

@@ -98,7 +98,7 @@ def arg_parser():
 
 def tf2paddle(model_path,
               save_dir,
-              without_data_format_optimization,
+              without_data_format_optimization=False,
               define_input_shape=False,
               params_merge=False):
     # check tensorflow installation and version
@@ -117,37 +117,24 @@ def tf2paddle(model_path,
             "[ERROR] Tensorflow is not installed, use \"pip install tensorflow\"."
         )
         return
-
+    from x2paddle import program
     from x2paddle.decoder.tf_decoder import TFDecoder
     from x2paddle.op_mapper.tf_op_mapper import TFOpMapper
-    from x2paddle.op_mapper.tf_op_mapper_nhwc import TFOpMapperNHWC
-    from x2paddle.optimizer.tf_optimizer import TFOptimizer
+    from x2paddle.optimizer.tensorflow.bias import BiasOpt
+    from x2paddle.optimizer.tensorflow.transpose import TransposeOpt
+    from x2paddle.optimizer.tensorflow.batch_norm import BatchNormOpt
 
     print("Now translating model from tensorflow to paddle.")
     model = TFDecoder(model_path, define_input_shape=define_input_shape)
-    if not without_data_format_optimization:
-        mapper = TFOpMapper(model)
-        optimizer = TFOptimizer(mapper)
-        # neccesary optimization
-        optimizer.delete_redundance_code()
-        # optimizer below is experimental
-        optimizer.optimize_elementwise_op()
-        optimizer.merge_activation()
-        optimizer.merge_bias()
-        optimizer.optimize_sub_graph()
-
-#        optimizer.merge_batch_norm()
-#        optimizer.merge_prelu()
-    else:
-        mapper = TFOpMapperNHWC(model)
-        optimizer = TFOptimizer(mapper)
-        optimizer.delete_redundance_code()
-        optimizer.strip_graph()
-        optimizer.merge_activation()
-        optimizer.merge_bias()
-        optimizer.make_nchw_input_output()
-        optimizer.remove_transpose()
-    mapper.save_inference_model(save_dir, params_merge)
+    mapper = TFOpMapper(model)
+    program.build()
+    bias_opt = BiasOpt()
+    transpose_opt = TransposeOpt()
+    batch_norm_opt = BatchNormOpt()
+    bias_opt.run(program)
+    batch_norm_opt.run(program)
+    transpose_opt.run(program)
+    program.gen_model(save_dir)
 
 
 def caffe2paddle(proto, weight, save_dir, caffe_proto, params_merge=False):

x2paddle/core/program.py

@@ -99,6 +99,53 @@ class PaddleGraph(object):
         self.layers[layer_id] = layer
         return layer_id
 
+    def del_layer(self, layer_id):
+        layer = self.layers[layer_id]
+        outputs = self.edges_out.get(layer_id, [])
+        inputs = self.edges_in.get(layer_id, [])
+
+        assert len(
+            inputs) <= 1, "There should be 0 or 1 input for deleted layer."
+
+        if len(inputs) == 0:
+            for out in outputs:
+                while layer_id in self.edges_in[out]:
+                    index = self.edges_in[out].index(layer_id)
+                    del self.edges_in[out][index]
+
+                input_keys = list(self.layers[out].inputs.keys())
+                for k in input_keys:
+                    if self.layers[out].inputs[k] == layer.outputs[0]:
+                        del self.layers[out].inputs[k]
+
+            del self.layers[layer_id]
+            if layer_id in self.edges_in:
+                del self.edges_in[layer_id]
+            if layer_id in self.edges_out:
+                del self.edges_out[layer_id]
+            return
+
+        # 将所有输出layer的输入layer进行替换
+        for out in outputs:
+            for i in range(len(self.edges_in[out])):
+                if self.edges_in[out][i] == layer_id:
+                    self.edges_in[out][i] = inputs[0]
+
+        # 将输出layer赋给输入layer的输出
+        replace_index = self.edges_out[inputs[0]].index(layer_id)
+        del self.edges_out[inputs[0]][replace_index]
+        for i, out in enumerate(outputs):
+            self.edges_out[inputs[0]].insert(replace_index + i, out)
+            for k, v in self.layers[out].inputs.items():
+                if v == layer.outputs[0]:
+                    self.layers[out].inputs[k] = list(layer.inputs.values())[0]
+
+        del self.layers[layer_id]
+        if layer_id in self.edges_out:
+            del self.edges_out[layer_id]
+        if layer_id in self.edges_in:
+            del self.edges_in[layer_id]
+
     def build(self, inputs=None, outputs=None):
         self.clear_edges()
         outputs_from_nodes = dict()

x2paddle/decoder/tf_decoder.py

@@ -89,6 +89,12 @@ class TFGraphNode(GraphNode):
         field = getattr(attr, attr.WhichOneof('value'))
         return tensor_util.MakeNdarray(field)
 
+    @property
+    def name(self):
+        if hasattr(self, 'index'):
+            return self.layer_name + "_p{}".format(self.index)
+        return self.layer_name
+
     def get_attr(self, name):
         if name not in self.layer.attr:
             return None

x2paddle/optimizer/tensorflow/batch_norm.py

+import copy
+from collections import OrderedDict
+from x2paddle.core.program import PaddleLayer
+
+
+class BatchNormOpt:
+    def __init__(self):
+        pass
+
+    def run(self, graph):
+        layers = copy.deepcopy(graph.layers)
+        for layer_id, layer in layers.items():
+            if layer.kernel != "fluid.layers.elementwise_add":
+                continue
+            axis = layer.attrs.get('axis', -1)
+            if axis != -1 and axis != 3:
+                continue
+
+            input_ids0 = graph.edges_in[layer_id]
+            mul_layer0 = graph.layers[input_ids0[0]]
+            sub_layer0 = graph.layers[input_ids0[1]]
+            if mul_layer0.kernel != "fluid.layers.elementwise_mul":
+                continue
+            if sub_layer0.kernel != "fluid.layers.elementwise_sub":
+                continue
+            axis = mul_layer0.attrs.get('axis', -1)
+            if axis != -1 and axis != 3:
+                continue
+            axis = sub_layer0.attrs.get('axis', -1)
+            if axis != -1 and axis != 0:
+                continue
+            if len(graph.edges_out.get(input_ids0[0], [])) != 1:
+                continue
+            if len(graph.edges_out.get(input_ids0[1], [])) != 1:
+                continue
+
+            input_ids1 = graph.edges_in[input_ids0[0]]
+            nhwc_input = graph.layers[input_ids1[0]]
+            mul_layer1 = graph.layers[input_ids1[1]]
+            if mul_layer1.kernel != "fluid.layers.elementwise_mul":
+                continue
+            axis = mul_layer1.attrs.get('axis', -1)
+            if axis != -1 and axis != 0:
+                continue
+            if len(graph.edges_out.get(input_ids1[1], [])) != 2:
+                continue
+
+            input_ids2 = graph.edges_in[input_ids0[1]]
+            beta = graph.layers[input_ids2[0]]
+            mul_layer2 = graph.layers[input_ids2[1]]
+            if beta.kernel != "fluid.layers.create_parameter":
+                continue
+            axis = mul_layer2.attrs.get('axis', -1)
+            if axis != -1 and axis != 0:
+                continue
+            if len(graph.edges_out.get(input_ids2[0], [])) != 1:
+                continue
+            if len(graph.edges_out.get(input_ids2[1], [])) != 1:
+                continue
+            if beta.outputs[0] not in graph.parameters:
+                continue
+            beta_shape = graph.parameters[beta.outputs[0]].shape
+            if len(beta_shape) != 1:
+                continue
+
+            input_ids3 = graph.edges_in[input_ids2[1]]
+            mean = graph.layers[input_ids3[0]]
+            mul_layer3 = graph.layers[input_ids3[1]]
+            if mean.kernel != "fluid.layers.create_parameter":
+                continue
+            axis = mul_layer3.attrs.get('axis', -1)
+            if axis != -1 and axis != 0:
+                continue
+            if len(graph.edges_out.get(input_ids3[0], [])) != 1:
+                continue
+            if len(graph.edges_out.get(input_ids3[1], [])) != 2:
+                continue
+            if mul_layer3.id != mul_layer1.id:
+                continue
+            if mean.outputs[0] not in graph.parameters:
+                continue
+            mean_shape = graph.parameters[mean.outputs[0]].shape
+            if mean_shape != beta_shape:
+                continue
+
+            input_ids4 = graph.edges_in[input_ids3[1]]
+            rsqrt_layer = graph.layers[input_ids4[0]]
+            gamma = graph.layers[input_ids4[1]]
+            if rsqrt_layer.kernel != "fluid.layers.rsqrt":
+                continue
+            if gamma.kernel != "fluid.layers.create_parameter":
+                continue
+            if len(graph.edges_out.get(input_ids4[0], [])) != 1:
+                continue
+            if len(graph.edges_out.get(input_ids4[1], [])) != 1:
+                continue
+            if gamma.outputs[0] not in graph.parameters:
+                continue
+            gamma_shape = graph.parameters[gamma.outputs[0]].shape
+            if gamma_shape != beta_shape:
+                continue
+
+            input_ids5 = graph.edges_in[input_ids4[0]]
+            add_layer = graph.layers[input_ids5[0]]
+            if add_layer.kernel != "fluid.layers.elementwise_add":
+                continue
+            axis = add_layer.attrs.get('axis', -1)
+            if axis != -1 and axis != 0:
+                continue
+            if len(graph.edges_out.get(input_ids5[0], [])) != 1:
+                continue
+
+            input_ids6 = graph.edges_in[input_ids5[0]]
+            variance = graph.layers[input_ids6[0]]
+            other = graph.layers[input_ids6[1]]
+            if variance.kernel != "fluid.layers.create_parameter":
+                continue
+            if other.kernel != "fluid.layers.create_parameter":
+                continue
+            if len(graph.edges_out.get(input_ids6[0], [])) != 1:
+                continue
+            if len(graph.edges_out.get(input_ids6[1], [])) != 1:
+                continue
+            if variance.outputs[0] not in graph.parameters:
+                continue
+            variance_shape = graph.parameters[variance.outputs[0]].shape
+            if variance_shape != beta_shape:
+                continue
+            if other.outputs[0] not in graph.parameters:
+                continue
+            if graph.parameters[other.outputs[0]].size != 1:
+                continue
+
+            ids = set([
+                layer_id, mul_layer0.id, sub_layer0.id, mul_layer1.id, beta.id,
+                mul_layer2.id, mean.id, mul_layer2.id, rsqrt_layer.id, gamma.id,
+                add_layer.id, variance.id, other.id
+            ])
+
+            for id in ids:
+                del graph.layers[id]
+                if id in graph.edges_in:
+                    del graph.edges_in[id]
+                if id in graph.edges_out:
+                    del graph.edges_out[id]
+
+            copy_layers = copy.deepcopy(graph.layers)
+            graph.layers = OrderedDict()
+            for k, v in copy_layers.items():
+                if k != nhwc_input.id:
+                    graph.layers[k] = v
+                    continue
+                graph.layers[k] = v
+                transpose0 = PaddleLayer(
+                    id='{}_1'.format(k),
+                    kernel="fluid.layers.transpose",
+                    inputs={"x": v.outputs[0]},
+                    outputs=["transpose_for_bn"],
+                    perm=[0, 3, 1, 2])
+                bn = PaddleLayer(
+                    id='{}_2'.format(k),
+                    kernel="fluid.layers.batch_norm",
+                    inputs={"input": "transpose_for_bn"},
+                    outputs=layer.outputs,
+                    epsilon=graph.parameters[other.outputs[0]],
+                    param_attr="'{}'".format(gamma.outputs[0]),
+                    bias_attr="'{}'".format(beta.outputs[0]),
+                    moving_mean_name="'{}'".format(mean.outputs[0]),
+                    moving_variance_name="'{}'".format(variance.outputs[0]))
+                transpose1 = PaddleLayer(
+                    id=layer_id,
+                    kernel="fluid.layers.transpose",
+                    inputs={"x": layer.outputs[0]},
+                    outputs=layer.outputs,
+                    perm=[0, 2, 3, 1])
+                graph.layers[transpose0.id] = transpose0
+                graph.layers[bn.id] = bn
+                graph.layers[transpose1.id] = transpose1
+        graph.build()

x2paddle/optimizer/tensorflow/bias.py

+import copy
+
+
+class BiasOpt:
+    def __init__(self):
+        self.conv_layers = [
+            'fluid.layers.conv2d', 'fluid.layers.conv2d_transpose'
+        ]
+        self.act_layers = [
+            'fluid.layers.relu', 'fluid.layers.relu6', 'fluid.layers.sigmoid',
+            'fluid.layers.exp', 'fluid.layers.tanh', 'fluid.layers.softplus',
+            'fluid.layers.leaky_relu'
+        ]
+
+    def run(self, graph):
+        layers = copy.deepcopy(graph.layers)
+        for layer_id, layer in layers.items():
+            if layer.kernel in self.conv_layers or layer.kernel == "fluid.layers.transpose":
+                if len(graph.edges_out.get(layer_id, [])) > 1:
+                    continue
+                if layer.outputs[0] in graph.outputs:
+                    continue
+
+                out_layer_id = graph.edges_out[layer_id][0]
+                if graph.layers[
+                        out_layer_id].kernel != "fluid.layers.elementwise_add":
+                    continue
+                if graph.layers[out_layer_id].attrs.get('axis', -1) != -1:
+                    continue
+
+                in_layer_id = graph.edges_in[out_layer_id]
+                bias_layer_id = in_layer_id[1 - in_layer_id.index(layer_id)]
+                if graph.layers[
+                        bias_layer_id].kernel != "fluid.layers.create_parameter":
+                    continue
+
+                bias_layer = graph.layers[bias_layer_id]
+                if len(bias_layer.attrs['shape']) != 1:
+                    continue
+                if len(graph.edges_out[bias_layer_id]) != 1:
+                    continue
+
+                if layer.kernel == "fluid.layers.transpose":
+                    if layer.attrs['perm'] != [0, 2, 3, 1]:
+                        continue
+                    in_layer_id = graph.edges_in[layer_id][0]
+                    if graph.layers[in_layer_id].kernel not in self.conv_layers:
+                        continue
+                    if graph.layers[in_layer_id].attrs['bias_attr'] != False:
+                        continue
+                    if graph.layers[in_layer_id].outputs[0] in graph.outputs:
+                        continue
+                    if len(graph.edges_out[in_layer_id]) != 1:
+                        continue
+                    graph.layers[in_layer_id].attrs[
+                        'bias_attr'] = bias_layer.attrs['name']
+                else:
+                    graph.layers[layer_id].attrs[
+                        'bias_attr'] = bias_layer.attrs['name']
+                bias_add_outs = graph.edges_out.get(out_layer_id, [])
+                bias_add_output = graph.layers[out_layer_id].outputs[0]
+                graph.del_layer(bias_layer_id)
+                graph.del_layer(out_layer_id)
+
+                for out in bias_add_outs:
+                    for k, v in graph.layers[out].inputs.items():
+                        if v == layer.outputs[0]:
+                            graph.layers[out].inputs[k] = bias_add_output
+                graph.layers[layer_id].outputs[0] = bias_add_output
+
+                if layer.kernel == "fluid.layers.transpose":
+                    in_layer_id = graph.edges_in[layer_id][0]
+                    graph.layers[in_layer_id].outputs[0] = bias_add_output
+                    graph.layers[layer_id].inputs['x'] = bias_add_output

x2paddle/optimizer/tensorflow/transpose.py

+import copy
+import sys
+
+
+class TransposeOpt:
+    def __init__(self):
+        self.image_layers = [
+            'fluid.layers.conv2d', 'fluid.layers.batch_norm',
+            'fluid.layers.conv2d_transpose', 'fluid.layers.resize_nearest',
+            'fluid.layers.resize_bilinear', 'fluid.layers.pool2d',
+            'fluid.layers.pad2d'
+        ]
+        self.direct_layers = [
+            'fluid.layers.relu', 'fluid.layers.relu6', 'fluid.layers.abs',
+            'fluid.layers.sigmoid', 'fluid.layers.exp', 'fluid.layers.rsqrt',
+            'fluid.layers.swish_f32', 'fluid.layers.tanh',
+            'fluid.layers.softplus', 'fluid.layers.leaky_relu',
+            'fluid.layers.floor', 'fluid.layers.erf', 'fluid.layers.swish'
+        ]
+        self.elementwise_layers = [
+            'fluid.layers.elementwise_add', 'fluid.layers.elementwise_sub',
+            'fluid.layers.elementwise_mul', 'fluid.layers.elementwise_div'
+        ]
+        #        self.reduce_layers = []
+        self.reduce_layers = [
+            'fluid.layers.reduce_mean', 'fluid.layers.reduce_all',
+            'fluid.layers.reduce_max', 'fluid.layers.reduce_any',
+            'fluid.layers.reduce_sum', 'fluid.layers.reduce_prod'
+        ]
+
+    def get_transpose_num(self, graph):
+        count = 0
+        for layer_id, layer in graph.layers.items():
+            if layer.kernel == "fluid.layers.transpose":
+                count += 1
+        return count
+
+    def run(self, graph):
+        total_layer_num = len(graph.layers)
+        scanned_layers = set()
+        optimized_transpose_layers = list()
+        optimized_reduce_layers = list()
+        optimized_concat_layers = list()
+        optimized_elementwise_layers = list()
+
+        def strip_transpose(_graph):
+            layers = copy.deepcopy(_graph.layers)
+            for layer_id, layer in layers.items():
+                if layer_id in scanned_layers:
+                    continue
+                scanned_layers.add(layer_id)
+                percent = round(len(scanned_layers) / total_layer_num * 100, 2)
+                sys.stderr.write("\rOptimize Transpose Layers...{}%".format(
+                    percent))
+
+                if layer.kernel != "fluid.layers.transpose":
+                    continue
+                if layer.attrs["perm"] != [0, 2, 3, 1]:
+                    continue
+                transpose_layers = list()
+                propagate_layers = list()
+                reduce_layers = list()
+                concat_layers = list()
+                # 此elementwise_layers专用于存储shape(4) + shape(1)的形式layer
+                elementwise_layers = list()
+                can_be_optimized = True
+                for out in _graph.edges_out.get(layer_id, []):
+                    if _graph.layers[out].kernel == "fluid.layers.transpose":
+                        if _graph.layers[out].attrs["perm"] != [0, 3, 1, 2]:
+                            can_be_optimized = False
+                            break
+                        transpose_layers.append(out)
+                    elif _graph.layers[out].kernel in self.elementwise_layers:
+                        propagate_layers.append(out)
+                    elif _graph.layers[out].kernel in self.direct_layers:
+                        if _graph.layers[out].outputs[0] in _graph.outputs:
+                            can_be_optimized = False
+                            break
+                        propagate_layers.append(out)
+                    elif _graph.layers[out].kernel in self.reduce_layers:
+                        if _graph.layers[out].outputs[0] in _graph.outputs:
+                            can_be_optimized = False
+                            break
+                        if not _graph.layers[out].attrs.get('keep_dim', False):
+                            can_be_optimized = False
+                            break
+                        propagate_layers.append(out)
+                        reduce_layers.append(out)
+                    elif _graph.layers[out].kernel == "fluid.layers.concat":
+                        if _graph.layers[out].outputs[0] in _graph.outputs:
+                            can_be_optimized = False
+                            break
+                        propagate_layers.append(out)
+                        concat_layers.append(out)
+                    else:
+                        can_be_optimized = False
+                        break
+
+                visited_layers = set()
+                while len(propagate_layers) > 0 and can_be_optimized:
+                    current_id = propagate_layers.pop(0)
+                    visited_layers.add(current_id)
+                    for out in _graph.edges_out.get(current_id, []):
+                        if _graph.layers[
+                                out].kernel == "fluid.layers.transpose":
+                            if _graph.layers[out].attrs["perm"] != [0, 3, 1, 2]:
+                                can_be_optimized = False
+                                break
+                            transpose_layers.append(out)
+                        elif _graph.layers[
+                                out].kernel in self.elementwise_layers:
+                            if _graph.layers[out].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if out not in visited_layers:
+                                propagate_layers.append(out)
+                        elif _graph.layers[out].kernel in self.direct_layers:
+                            if _graph.layers[out].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if out not in visited_layers:
+                                propagate_layers.append(out)
+                        elif _graph.layers[out].kernel in self.reduce_layers:
+                            if _graph.layers[out].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if not _graph.layers[out].attrs.get('keep_dim',
+                                                                False):
+                                can_be_optimized = False
+                                break
+                            if out not in visited_layers:
+                                propagate_layers.append(out)
+                                reduce_layers.append(out)
+                        elif _graph.layers[out].kernel == "fluid.layers.concat":
+                            if _graph.layers[out].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if out not in visited_layers:
+                                propagate_layers.append(out)
+                                concat_layers.append(out)
+                        else:
+                            can_be_optimized = False
+                            break
+                    for ipt in _graph.edges_in.get(current_id, []):
+                        if _graph.layers[
+                                current_id].kernel in self.elementwise_layers:
+                            try:
+                                x_shape = _graph.layers[
+                                    current_id].input_shapes['x']
+                                y_shape = _graph.layers[
+                                    current_id].input_shapes['y']
+                                if _graph.layers[ipt].outputs[
+                                        0] == _graph.layers[current_id].inputs[
+                                            'x']:
+                                    if len(x_shape) <= 1:
+                                        elementwise_layers.append(current_id)
+                                        continue
+                                elif _graph.layers[ipt].outputs[
+                                        0] == _graph.layers[current_id].inputs[
+                                            'y']:
+                                    if len(y_shape) <= 1:
+                                        elementwise_layers.append(current_id)
+                                        continue
+                                else:
+                                    raise Exception(
+                                        "Unexcepted situation happend while optimizing transpose"
+                                    )
+                            except Exception as e:
+                                can_be_optimized = False
+                                break
+                        if _graph.layers[
+                                ipt].kernel == "fluid.layers.transpose":
+                            if _graph.layers[ipt].attrs["perm"] != [0, 2, 3, 1]:
+                                can_be_optimized = False
+                                break
+                            if ipt not in visited_layers:
+                                transpose_layers.append(ipt)
+                        elif _graph.layers[
+                                ipt].kernel in self.elementwise_layers:
+                            if _graph.layers[ipt].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if ipt not in visited_layers:
+                                propagate_layers.append(ipt)
+                        elif _graph.layers[ipt].kernel in self.direct_layers:
+                            if _graph.layers[ipt].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if ipt not in visited_layers:
+                                propagate_layers.append(ipt)
+                        elif _graph.layers[ipt].kernel in self.reduce_layers:
+                            if _graph.layers[ipt].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if not _graph.layers[ipt].attrs.get('keep_dim',
+                                                                False):
+                                can_be_optimized = False
+                                break
+                            if ipt not in visited_layers:
+                                propagate_layers.append(ipt)
+                                reduce_layers.append(ipt)
+                        elif _graph.layers[ipt].kernel == "fluid.layers.concat":
+                            if _graph.layers[ipt].outputs[0] in _graph.outputs:
+                                can_be_optimized = False
+                                break
+                            if ipt not in visited_layers:
+                                propagate_layers.append(ipt)
+                                concat_layers.append(ipt)
+                        else:
+                            can_be_optimized = False
+                            break
+                    if not can_be_optimized:
+                        break
+                if not can_be_optimized:
+                    continue
+
+                transpose_layers.append(layer_id)
+                transpose_layers = list(set(transpose_layers))
+                for l in transpose_layers:
+                    if graph.layers[l].outputs[0] in graph.outputs:
+                        can_be_optimized = False
+                        break
+                if not can_be_optimized:
+                    continue
+
+                for l in transpose_layers:
+                    _graph.del_layer(l)
+
+                optimized_transpose_layers.extend(transpose_layers)
+                optimized_reduce_layers.extend(reduce_layers)
+                optimized_concat_layers.extend(concat_layers)
+                optimized_elementwise_layers.extend(elementwise_layers)
+                return True
+            return False
+
+        before_transpose_num = self.get_transpose_num(graph)
+        opt_graph = copy.deepcopy(graph)
+        total_layer_num = len(opt_graph.layers)
+
+        while strip_transpose(opt_graph):
+            pass
+
+        for layer_id in list(set(optimized_transpose_layers)):
+            graph.del_layer(layer_id)
+        for layer_id in list(set(optimized_reduce_layers)):
+            dim = graph.layers[layer_id].attrs.get('dim', None)
+            if dim is not None:
+                for i in range(len(dim)):
+                    dim[i] = [0, 2, 3, 1][dim[i]]
+                graph.layers[layer_id].attrs['dim'] = dim
+        for layer_id in list(set(optimized_concat_layers)):
+            axis = graph.layers[layer_id].attrs.get('axis', 0)
+            graph.layers[layer_id].attrs['axis'] = [0, 2, 3, 1][axis]
+        for layer_id in list(set(optimized_elementwise_layers)):
+            axis = graph.layers[layer_id].attrs.get('axis', -1)
+            graph.layers[layer_id].attrs['axis'] = [0, 2, 3, 1][axis]
+
+        current_transpose_num = self.get_transpose_num(graph)
+        print(
+            "\nTranspose layers optimized, before: transpose_num={}, after: transpose_num={}".
+            format(before_transpose_num, current_transpose_num))