Question

我有以下文件：

model.ckpt-2400.data-00000-of-00001
model.ckpt-2400.index
model.ckpt-2400.meta

我希望以.pb的形式保存它们，并具有以下功能：

def freeze_graph(model_dir, output_node_names):
    """Extract the sub graph defined by the output nodes and convert all its variables into constant 
    Args:
    model_dir: the root folder containing the checkpoint state file
    output_node_names: a string, containing all the output node's names, 
                        comma separated
    """
    if not tf.gfile.Exists(model_dir):
        raise AssertionError(
            "Export directory doesn't exists. Please specify an export "
            "directory: %s" % model_dir)

    if not output_node_names:
        print("You need to supply the name of a node to --output_node_names.")
        return -1

    # We retrieve our checkpoint fullpath
    checkpoint = tf.train.get_checkpoint_state(model_dir)
    input_checkpoint = checkpoint.model_checkpoint_path

    # We precise the file fullname of our freezed graph
    absolute_model_dir = "/".join(input_checkpoint.split('/')[:-1])
    output_graph = absolute_model_dir + "/frozen_model.pb"

    # We clear devices to allow TensorFlow to control on which device it will load operations
    clear_devices = True

    # We start a session using a temporary fresh Graph
    with tf.Session(graph=tf.Graph()) as sess:
        # We import the meta graph in the current default Graph
        saver = tf.train.import_meta_graph(input_checkpoint + '.meta', clear_devices=clear_devices)

        # We restore the weights
        saver.restore(sess, input_checkpoint)

        # We use a built-in TF helper to export variables to constants
        output_graph_def = tf.graph_util.convert_variables_to_constants(
            sess, # The session is used to retrieve the weights
            tf.get_default_graph().as_graph_def(), # The graph_def is used to retrieve the nodes 
            output_node_names.split(",") # The output node names are used to select the usefull nodes
        ) 

        # Finally we serialize and dump the output graph to the filesystem
        with tf.gfile.GFile(output_graph, "wb") as f:
            f.write(output_graph_def.SerializeToString())
        print("%d ops in the final graph." % len(output_graph_def.node))

    return output_graph_def

问题在于，当我使用tf.get_default_graph().as_graph_def().node时，它会返回[]。一个空数组。我没有可用于此的输出节点名称。

那么我怎样才能将它们保存为.pb？我应该参考tf.python.tools.freeze_graph.freeze_graph()函数吗？

Answer 1

原来我需要做的就是提供输出节点的名称...我在我的代码的另一部分中，被指定为记录的节点来检查结果。

predictions = {
      # Generate predictions (for PREDICT and EVAL mode)
      "classes": tf.argmax(input=logits, axis=1),
      # Add `softmax_tensor` to the graph. It is used for PREDICT and by the
      # `logging_hook`.
      "probabilities": tf.nn.softmax(logits, name="softmax_tensor") #This one
  }

就我而言，它是softmax_tensor。

Tensorflow - 将检查点文件保存为.pb，但没有输出节点名称

1 个答案: