diff --git a/x2paddle/op_mapper/tf_op_mapper.py b/x2paddle/op_mapper/tf_op_mapper.py index 847ebc8b96aab160b1747c1bb73a7fe6ecd4dae0..2a7a6082997a442e00aa6f876ceef3536817be80 100644 --- a/x2paddle/op_mapper/tf_op_mapper.py +++ b/x2paddle/op_mapper/tf_op_mapper.py @@ -168,7 +168,11 @@ class TFOpMapper(OpMapper): x_input = y y_input = x x_shape = y.out_shapes[0] + if len(x_shape) == 0: + x_shape = [1] y_shape = x.out_shapes[0] + if len(y_shape) == 0: + y_shape = [1] else: if len(x_shape) == 1 and len(y_shape) == 4 and x_shape[ 0] == y_shape[-1] and y_shape.count(-1) < 1: diff --git a/x2paddle/op_mapper/tf_op_mapper_nhwc.py b/x2paddle/op_mapper/tf_op_mapper_nhwc.py index 24fd7de2a1787a03141909b8f55c5d5ff734b563..bf1786996ec86818b8a7205ebc17d825fb875651 100644 --- a/x2paddle/op_mapper/tf_op_mapper_nhwc.py +++ b/x2paddle/op_mapper/tf_op_mapper_nhwc.py @@ -121,10 +121,29 @@ class TFOpMapperNHWC(OpMapper): pd_param_name = list(param.values())[0] tf_param = node.get_attr(tf_param_name) attr[pd_param_name] = tf_param - node.fluid_code.add_layer(op_info[0], - inputs=input, - output=node, - param_attr=attr) + + if len(input.out_shapes[0]) == 4 and op_info[0] != 'shape': + attr1 = {"perm": [0, 3, 1, 2]} + node.fluid_code.add_layer('transpose', + inputs=input, + output=node, + param_attr=attr1) + input = node + node.fluid_code.add_layer(op_info[0], + inputs=input, + output=node, + param_attr=attr) + input = node + attr2 = {"perm": [0, 2, 3, 1]} + node.fluid_code.add_layer('transpose', + inputs=input, + output=node, + param_attr=attr2) + else: + node.fluid_code.add_layer(op_info[0], + inputs=input, + output=node, + param_attr=attr) def elementwise_map(self, node): assert node.layer_type in self.elementwise_ops @@ -149,7 +168,11 @@ class TFOpMapperNHWC(OpMapper): x_input = y y_input = x x_shape = y.out_shapes[0] + if len(x_shape) == 0: + x_shape = [1] y_shape = x.out_shapes[0] + if len(y_shape) == 0: + y_shape = [1] else: raise Exception("Unexpected situation happend") @@ -193,11 +216,30 @@ class TFOpMapperNHWC(OpMapper): output="y_tmp", param_attr=attr) y_input = "y_tmp" - inputs = {"x": x_input, "y": y_input} - node.fluid_code.add_layer(op_type, - inputs=inputs, - output=node, - param_attr=None) + if len(x_shape) == 4 and len(y_shape) == 4: + node.fluid_code.add_layer("transpose", + inputs=x_input, + output=x_input, + param_attr={'perm': [0, 3, 1, 2]}) + node.fluid_code.add_layer("transpose", + inputs=y_input, + output=y_input, + param_attr={'perm': [0, 3, 1, 2]}) + inputs = {"x": x_input, "y": y_input} + node.fluid_code.add_layer(op_type, + inputs=inputs, + output=node, + param_attr=None) + node.fluid_code.add_layer("transpose", + inputs=node, + output=node, + param_attr={'perm': [0, 2, 3, 1]}) + else: + inputs = {"x": x_input, "y": y_input} + node.fluid_code.add_layer(op_type, + inputs=inputs, + output=node, + param_attr=None) def Placeholder(self, node): shape = node.out_shapes[0] @@ -978,9 +1020,7 @@ class TFOpMapperNHWC(OpMapper): if pad_mode == "SAME": if node.tf_data_format == "NHWC": - print(out_shape) out_shape = [out_shape[i] for i in [0, 3, 1, 2]] - print(out_shape) for i in range(4): if out_shape[i] < 0: out_shape[i] = 999999 diff --git a/x2paddle/optimizer/tf_optimizer.py b/x2paddle/optimizer/tf_optimizer.py index 99156844a24c619e15d83be2d9345feba73b7e3e..848409cabb898d75c0b2d07c08e758caefcd4899 100644 --- a/x2paddle/optimizer/tf_optimizer.py +++ b/x2paddle/optimizer/tf_optimizer.py @@ -232,84 +232,35 @@ class TFOptimizer(object): 'act'] node.fluid_code.clear() self.graph.remove_node(node.layer_name) + self.graph.identity_map[node.layer_name] = input.layer_name def remove_transpose(self): graph_copy = cp.deepcopy(self.graph) nhwc_insensitive_ops = [ 'Relu', 'Relu6', 'Abs', 'Sigmoid', 'Exp', 'Rsqrt', 'swish_f32', - 'LeakyRelu', 'Cast' + 'LeakyRelu', 'Cast', 'Tanh' ] elementwise_ops = [ 'Sub', 'Add', 'RealDiv', 'Maximum', 'Mul', 'FloorDiv', 'GreaterEqual' ] - for node_name in self.graph.topo_sort: - node = graph_copy.get_node(node_name) - if node is None: - continue - if node.layer_type in nhwc_insensitive_ops: - graph_copy.remove_node(node_name) - optimize_ops = [ 'Conv2D', 'MaxPool', 'FusedBatchNorm', 'DepthwiseConv2dNative', 'AvgPool', 'Pad', 'Conv2DBackpropInput', 'ResizeNearestNeighbor', 'ResizeBilinear', "Placeholder" ] + can_be_optimized_ops = [ + 'Conv2D', 'MaxPool', 'FusedBatchNorm', 'DepthwiseConv2dNative', + 'AvgPool', 'Pad', 'Conv2DBackpropInput', 'ResizeNearestNeighbor', + 'ResizeBilinear', "Placeholder", 'Relu', 'Relu6', 'Abs', 'Sigmoid', + 'Exp', 'Rsqrt', 'swish_f32', 'LeakyRelu', 'Cast', 'Tanh' + ] for node_name in self.graph.topo_sort: node = graph_copy.get_node(node_name) if node is None: continue - if node.layer_type in elementwise_ops: - is_nhwc = True - for in_name in node.inputs: - in_node = graph_copy.get_node(in_name) - if hasattr(in_node, "is_nhwc"): - if not in_node.is_nhwc: - is_nhwc = False - else: - if len(in_node.fluid_code.layers) < 2: - is_nhwc = False - continue - if in_node.fluid_code.layers[ - -1].op != "transpose" or in_node.fluid_code.layers[ - -1].param_attr["perm"] != [0, 2, 3, 1]: - is_nhwc = False - continue - node.is_nhwc = is_nhwc - - for i in range(len(self.graph.topo_sort)): - node_name = self.graph.topo_sort[-1 * i - 1] - node = graph_copy.get_node(node_name) - if node is None: - continue - if node.layer_type in elementwise_ops: - can_be_removed = True - if len(node.fluid_code.layers) > 1: - can_be_removed = False - if not node.is_nhwc: - can_be_removed = False - for out_name in node.outputs: - out_node = graph_copy.get_node(out_name) - if hasattr(out_node, "is_nhwc"): - if not out_node.is_nhwc: - can_be_removed = False - else: - if len(out_node.fluid_code.layers) < 2: - can_be_removed = False - break - if out_node.fluid_code.layers[ - 0].op != "transpose" or out_node.fluid_code.layers[ - 0].param_attr["perm"] != [0, 3, 1, 2]: - can_be_removed = False - break - node.can_be_removed = can_be_removed - - for node_name in self.graph.topo_sort: - node = graph_copy.get_node(node_name) - if node is None: - continue - if node.layer_type in optimize_ops: + if node.layer_type in can_be_optimized_ops: if node.fluid_code.layers[ -1].op != "transpose" or node.fluid_code.layers[ -1].param_attr["perm"] != [0, 2, 3, 1]: @@ -327,6 +278,9 @@ class TFOptimizer(object): 0].param_attr["perm"] != [0, 3, 1, 2]: can_be_removed = False break + elif out_node.layer_type in elementwise_ops: + can_be_removed = False + break if can_be_removed and len(node.fluid_code.layers) > 1: true_node = self.graph.get_node(node_name) if true_node.layer_type == "Placeholder": @@ -346,8 +300,6 @@ class TFOptimizer(object): del true_node.fluid_code.layers[-1] for out_name in output_names: out_node = self.graph.get_node(out_name) - if out_node.layer_type in elementwise_ops: - continue out_node.fluid_code.layers[ 1].inputs = out_node.fluid_code.layers[0].inputs del out_node.fluid_code.layers[0] @@ -357,43 +309,178 @@ class TFOptimizer(object): if node is None: continue if node.layer_type in elementwise_ops: - if not node.can_be_removed: + can_be_removed = True + if node.fluid_code.layers[ + -1].op != "transpose" or node.fluid_code.layers[ + -1].param_attr["perm"] != [0, 2, 3, 1]: + continue + can_be_removed = True + + output_names = node.outputs + for out_name in output_names: + out_node = graph_copy.get_node(out_name) + if len(out_node.fluid_code.layers) < 3: + can_be_removed = False + break + if hasattr(out_node, "can_be_removed"): + if not out_node.can_be_removed: + can_be_removed = False + break + if out_node.layer_type in can_be_optimized_ops: + if out_node.fluid_code.layers[ + 0].op != "transpose" or out_node.fluid_code.layers[ + 0].param_attr["perm"] != [0, 3, 1, 2]: + can_be_removed = False + break + elif out_node.layer_type in elementwise_ops: + if out_node.fluid_code.layers[ + 0].op != "transpose" and out_node.fluid_code.layers[ + 1].op != "transpose": + can_be_removed = False + break + if out_node.fluid_code.layers[0].op == "transpose": + if out_node.fluid_code.layers[0].param_attr[ + "perm"] != [0, 3, 1, 2]: + can_be_removed = False + break + if out_node.fluid_code.layers[1].op == "transpose": + if out_node.fluid_code.layers[1].param_attr[ + "perm"] != [0, 3, 1, 2]: + can_be_removed = False + break + + if can_be_removed and len(node.fluid_code.layers) > 1: true_node = self.graph.get_node(node_name) - for i, in_name in enumerate(node.inputs): - in_node = graph_copy.get_node(in_name) - if hasattr(in_node, "is_nhwc") and in_node.is_nhwc: - if i == 0: - l = Layer() - l.op = "transpose" - l.inputs = true_node.fluid_code.layers[ - 0].inputs["x"] - l.param_attr = {"perm": [0, 2, 3, 1]} - l.output = "nhwc_" + l.inputs.layer_name - true_node.fluid_code.layers[0].inputs[ - "x"] = l.output - true_node.fluid_code.layers.insert(0, l) - elif i == 1: - l = Layer() - l.op = "transpose" - l.inputs = true_node.fluid_code.layers[ - 0].inputs["y"] - l.param_attr = {"perm": [0, 2, 3, 1]} - l.output = "nhwc_" + l.inputs.layer_name - true_node.fluid_code.layers[0].inputs[ - "y"] = l.output - true_node.fluid_code.layers.insert(0, l) - else: - raise Exception("Unexpected situation happend") + true_node.fluid_code.layers[ + -2].output = true_node.fluid_code.layers[-1].output + del true_node.fluid_code.layers[-1] + for out_name in output_names: + out_node = self.graph.get_node(out_name) + if out_node.layer_type in can_be_optimized_ops: + out_node.fluid_code.layers[ + 1].inputs = out_node.fluid_code.layers[0].inputs + del out_node.fluid_code.layers[0] + elif out_node.layer_type in elementwise_ops: + if out_node.inputs[0] in node.layer_name: + if out_node.fluid_code.layers[ + 1].op == 'transpose': + out_node.fluid_code.layers[2].inputs[ + 'x'] = out_node.fluid_code.layers[ + 0].inputs + del out_node.fluid_code.layers[0] + else: + out_node.fluid_code.layers[1].inputs[ + 'x'] = out_node.fluid_code.layers[ + 0].inputs + del out_node.fluid_code.layers[0] + elif out_node.inputs[1] in node.layer_name: + if out_node.fluid_code.layers[ + 1].op == 'transpose': + out_node.fluid_code.layers[2].inputs[ + 'y'] = out_node.fluid_code.layers[ + 1].inputs + del out_node.fluid_code.layers[1] + else: + out_node.fluid_code.layers[1].inputs[ + 'y'] = out_node.fluid_code.layers[ + 0].inputs + del out_node.fluid_code.layers[0] + graph_copy = cp.deepcopy(self.graph) + for node_name in self.graph.topo_sort: + node = graph_copy.get_node(node_name) + if node is None or len(node.fluid_code.layers) < 2: + continue + if node.layer_type in can_be_optimized_ops and node.layer_type != "Placeholder": + if node.fluid_code.layers[ + -1].op != "transpose" or node.fluid_code.layers[ + -1].param_attr["perm"] != [0, 2, 3, 1]: continue - else: - for out_name in node.outputs: + can_be_removed = True + output_names = node.outputs + for out_name in output_names: + out_node = graph_copy.get_node(out_name) + if hasattr(out_node, "can_be_removed"): + if not out_node.can_be_removed: + can_be_removed = False + break + if len(out_node.fluid_code.layers) < 2: + can_be_removed = False + break + if out_node.layer_type in can_be_optimized_ops: + if out_node.fluid_code.layers[ + 0].op != "transpose" or out_node.fluid_code.layers[ + 0].param_attr["perm"] != [0, 3, 1, 2]: + can_be_removed = False + break + elif out_node.layer_type in elementwise_ops: + if out_node.fluid_code.layers[ + 0].op != "transpose" and out_node.fluid_code.layers[ + 1].op != "transpose": + can_be_removed = False + break + if out_node.fluid_code.layers[ + 0].op == "expand" or out_node.fluid_code.layers[ + 1].op == "expand": + can_be_removed = False + break + if out_node.fluid_code.layers[0].op == "transpose": + if out_node.fluid_code.layers[0].param_attr[ + "perm"] != [0, 3, 1, 2]: + can_be_removed = False + break + if out_node.fluid_code.layers[1].op == "transpose": + if out_node.fluid_code.layers[1].param_attr[ + "perm"] != [0, 3, 1, 2]: + can_be_removed = False + break + elif out_node.layer_type not in elementwise_ops and out_node.layer_type not in can_be_optimized_ops: + can_be_removed = False + break + + if can_be_removed: + true_node = self.graph.get_node(node_name) + if len(true_node.fluid_code.layers) < 2: + continue + true_node.fluid_code.layers[ + -2].output = true_node.fluid_code.layers[-1].output + del true_node.fluid_code.layers[-1] + for out_name in output_names: out_node = self.graph.get_node(out_name) - if out_node.layer_type not in elementwise_ops: - assert out_node.fluid_code.layers[ - 0].op == "transpose", "unexpected situation happend" + if out_node.layer_type in can_be_optimized_ops: out_node.fluid_code.layers[ 1].inputs = out_node.fluid_code.layers[0].inputs del out_node.fluid_code.layers[0] + elif out_node.layer_type in elementwise_ops: + if out_node.inputs[0] in node.layer_name: + if out_node.fluid_code.layers[ + 1].op == 'transpose': + if out_node.fluid_code.layers[ + 2].op == 'transpose': + out_node.fluid_code.layers[3].inputs[ + 'x'] = out_node.fluid_code.layers[ + 0].inputs + else: + out_node.fluid_code.layers[2].inputs[ + 'x'] = out_node.fluid_code.layers[ + 0].inputs + del out_node.fluid_code.layers[0] + else: + out_node.fluid_code.layers[1].inputs[ + 'x'] = out_node.fluid_code.layers[ + 0].inputs + del out_node.fluid_code.layers[0] + elif out_node.inputs[1] in node.layer_name: + if out_node.fluid_code.layers[ + 1].op == 'transpose': + out_node.fluid_code.layers[2].inputs[ + 'y'] = out_node.fluid_code.layers[ + 1].inputs + del out_node.fluid_code.layers[1] + else: + out_node.fluid_code.layers[1].inputs[ + 'y'] = out_node.fluid_code.layers[ + 0].inputs + del out_node.fluid_code.layers[0] def make_nchw_input_output(self): for i, name in enumerate(self.graph.input_nodes):