99773d6efd4c081424bdbc3ee9871cdf3e1bdb5c,autokeras/graph.py,Graph,to_add_skip_model,#Graph#Any#Any#,239

Before Change

        layer = WeightedAdd()
        single_input_shape = get_int_tuple(start.output_shape)
        layer.build([single_input_shape, single_input_shape])
        self._add_edge(layer, new_node_id, self.adj_list[output_id][0][0], False)
        self._add_edge(layer, input_id, self.adj_list[output_id][0][0], False)

        self._redirect_edge(output_id, self.adj_list[output_id][0][0], new_node_id)
        return self.produce_model()

    def to_conv_deeper_model(self, target, kernel_size):
        new_layers = deeper_conv_block(target, kernel_size)

After Change

                    q.put(v)
        return order_list

    def to_add_skip_model(self, start, end):
        conv_input_id = self.node_to_id[start.input]
        relu_input_id = self.adj_list[self.node_to_id[end.output]][0][0]

        // Add the pooling layer chain.
        pooling_layer_list = self.get_pooling_layers(conv_input_id, relu_input_id)
        skip_output_id = conv_input_id
        for index, layer_id in enumerate(pooling_layer_list):
            layer = self.layer_list[layer_id]
            self._add_node(index)
            new_node_id = self.node_to_id[index]
            self._add_edge(copy_layer(layer), skip_output_id, new_node_id, False)
            skip_output_id = new_node_id

        // Add the weighted add layer.
        self._add_node("a")
        new_node_id = self.node_to_id["a"]
        layer = WeightedAdd()
        single_input_shape = get_int_tuple(start.output_shape)
        layer.build([single_input_shape, single_input_shape])

        relu_output_id = self.adj_list[relu_input_id][0][0]
        self._redirect_edge(relu_input_id, relu_output_id, new_node_id)
        self._add_edge(layer, new_node_id, relu_output_id, False)
        self._add_edge(layer, skip_output_id, relu_output_id, False)

        return self.produce_model()

Instances