替换Tensorflow v2的占位符

替换Tensorflow v2的占位符 使您的代码与TF 2.0一起使用

以下是可与TF
2.0一起使用的示例代码。它依赖于可
通过以下方式访问的兼容性API

tensorflow.compat.v1

，并且需要禁用v2行为。我不知道它的行为是否符合您的预期。如果没有，请向我们提供更多有关您要实现的目标的说明。

import tensorflow.compat.v1 as tftf.disable_v2_behavior()@tf.functiondef construct_graph(graph_dict, inputs, outputs):    queue = inputs[:]    make_dict = {}    for key, val in graph_dict.items():        if key in inputs: make_dict[key] = tf.placeholder(tf.float32, name=key)        else: make_dict[key] = None    # Breadth-First search of graph starting from inputs    while len(queue) != 0:        cur = graph_dict[queue[0]]        for outg in cur["outgoing"]: if make_dict[outg[0]]: # If discovered node, do add/multiply operation     make_dict[outg[0]] = tf.add(make_dict[outg[0]], tf.multiply(outg[1], make_dict[queue[0]])) else: # If undiscovered node, input is just coming in multiplied and add outgoing to queue     make_dict[outg[0]] = tf.multiply(make_dict[queue[0]], outg[1])     for outgo in graph_dict[outg[0]]["outgoing"]:         queue.append(outgo[0])        queue.pop(0)    # Returns one data graph for each output    return [make_dict[x] for x in outputs]def main():    graph_def = {        "B": { "incoming": [], "outgoing": [("A", 1.0)]        },        "C": { "incoming": [], "outgoing": [("A", 1.0)]        },        "A": { "incoming": [("B", 2.0), ("C", -1.0)], "outgoing": [("D", 3.0)]        },        "D": { "incoming": [("A", 2.0)], "outgoing": []        }    }    outputs = construct_graph(graph_def, ["B", "C"], ["A"])    print(outputs)if __name__ == "__main__":    main()[<tf.Tensor 'PartitionedCall:0' shape=<unknown> dtype=float32>]

将您的代码迁移到TF 2.0

尽管以上代码段有效，但仍与TF 1.0绑定。要将其迁移到TF 2.0，您必须重构一点代码。

建议您不要返回的列表，而不是返回TF 1.0中可调用的张量的列表

keras.layers.Model

。

下面是一个工作示例：

import tensorflow as tfdef construct_graph(graph_dict, inputs, outputs):    queue = inputs[:]    make_dict = {}    for key, val in graph_dict.items():        if key in inputs: # Use keras.Input instead of placeholders make_dict[key] = tf.keras.Input(name=key, shape=(), dtype=tf.dtypes.float32)        else: make_dict[key] = None    # Breadth-First search of graph starting from inputs    while len(queue) != 0:        cur = graph_dict[queue[0]]        for outg in cur["outgoing"]: if make_dict[outg[0]] is not None: # If discovered node, do add/multiply operation     make_dict[outg[0]] = tf.keras.layers.add([         make_dict[outg[0]],         tf.keras.layers.multiply(  [[outg[1]], make_dict[queue[0]]],         )],     ) else: # If undiscovered node, input is just coming in multiplied and add outgoing to queue     make_dict[outg[0]] = tf.keras.layers.multiply(         [make_dict[queue[0]], [outg[1]]]     )     for outgo in graph_dict[outg[0]]["outgoing"]:         queue.append(outgo[0])        queue.pop(0)    # Returns one data graph for each output    model_inputs = [make_dict[key] for key in inputs]    model_outputs = [make_dict[key] for key in outputs]    return [tf.keras.Model(inputs=model_inputs, outputs=o) for o in model_outputs]def main():    graph_def = {        "B": { "incoming": [], "outgoing": [("A", 1.0)]        },        "C": { "incoming": [], "outgoing": [("A", 1.0)]        },        "A": { "incoming": [("B", 2.0), ("C", -1.0)], "outgoing": [("D", 3.0)]        },        "D": { "incoming": [("A", 2.0)], "outgoing": []        }    }    outputs = construct_graph(graph_def, ["B", "C"], ["A"])    print("Builded models:", outputs)    for o in outputs:        o.summary(120)        print("Output:", o((1.0, 1.0)))if __name__ == "__main__":    main()

这里要注意什么？

• 从更改

  placeholder

  为

  keras.Input

  ，需要设置输入的形状。
• 使用

  keras.layers.[add|multiply]

  的计算。这可能不是必需的，而是坚持使用一个界面。但是，它需要将因子包装在列表中（以处理批处理）
• 建立

  keras.Model

  返回
• 用值的元组调用模型（不再是字典）

这是代码的输出。

Builded models: [<tensorflow.python.keras.engine.training.Model object at 0x7fa0b49f0f50>]Model: "model"________________________________________________________________________________________________________________________Layer (type)     Output Shape    Param #       Connected to      ========================================================================================================================B (InputLayer)   [(None,)]       0         ________________________________________________________________________________________________________________________C (InputLayer)   [(None,)]       0         ________________________________________________________________________________________________________________________tf_op_layer_mul (TensorFlowOpLayer)    [(None,)]       0  B[0][0]________________________________________________________________________________________________________________________tf_op_layer_mul_1 (TensorFlowOpLayer)  [(None,)]       0  C[0][0]________________________________________________________________________________________________________________________add (Add)        (None,)         0  tf_op_layer_mul[0][0]tf_op_layer_mul_1[0][0]      ========================================================================================================================Total params: 0Trainable params: 0Non-trainable params: 0________________________________________________________________________________________________________________________Output: tf.Tensor([2.], shape=(1,), dtype=float32)