Python 初始Resnet V2模型冻结

我使用InceptionResNet v2模型来训练一个使用转移学习的图像分类模型。我的模型很好用。问题在于冻结模型。 目前，我有：

model.ckpt.meta model.ckpt.index model.ckpt 我使用教程通过将输出节点名称设置为InceptionResnetV2/Logits/Predictions来冻结模型，并且模型生成正确。我现在有一个名为model.pb的新文件

用于生成以冻结模型的代码：

import os

import tensorflow as tf
from tensorflow.python.framework import graph_util

dir = os.path.dirname(os.path.realpath(__file__))


def freeze_graph(model_folder, output_node_names):
    # We retrieve our checkpoint fullpath
    checkpoint = tf.train.get_checkpoint_state(model_folder)
    input_checkpoint = checkpoint.model_checkpoint_path

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

    # Before exporting our graph, we need to precise what is our output node
    # This is how TF decides what part of the Graph he has to keep and what part it can dump
    # NOTE: this variable is plural, because you can have multiple output nodes
    # output_node_names = "Accuracy/predictions"

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

    # We import the meta graph and retrieve a Saver
    saver = tf.train.import_meta_graph(input_checkpoint + '.meta', clear_devices=clear_devices)

    # We retrieve the protobuf graph definition
    graph = tf.get_default_graph()
    input_graph_def = graph.as_graph_def()

    # We start a session and restore the graph weights
    with tf.Session() as sess:
        saver.restore(sess, input_checkpoint)

        # We use a built-in TF helper to export variables to constants
        output_graph_def = graph_util.convert_variables_to_constants(
            sess,  # The session is used to retrieve the weights
            input_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))

当我想为这个模型提供输入时，问题就来了

首先，我使用以下方法加载模型图：

def load_graph(frozen_graph_filename):
    # We load the protobuf file from the disk and parse it to retrieve the
    # unserialized graph_def
    with tf.gfile.GFile(frozen_graph_filename, "rb") as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())

    # Then, we can use again a convenient built-in function to import a graph_def into the
    # current default Graph
    with tf.Graph().as_default() as graph:
        tf.import_graph_def(
            graph_def,
            input_map=None,
            return_elements=None,
            name="prefix",
            op_dict=None,
            producer_op_list=None
        )
    return graph

然后，当我浏览图形ops时，我没有找到输入占位符

for op in graph.get_operations():
    print(op.name)

第一个输入显示为：

前缀/批处理/先进先出队列 前缀/批处理/n 前缀/批次 前缀/接收resnetv2/Conv2d_1a_3x3/权重 前缀/接收resnetv2/Conv2d_1a_3x3/权重/读取 前缀/接收resnetv2/Conv2d_1a_3x3/卷积 前缀/接收resnetv2/Conv2d_1a_3x3/BatchNorm/beta 前缀/接收resnetv2/Conv2d_1a_3x3/BatchNorm/beta/read 前缀/接收resnetv2/Conv2d_1a_3x3/BatchNorm/矩/平均值/缩减指数 . . . 前缀/接收resnetv2/登录/预测

当我使用以下命令馈送图像时出现的错误：

    img_path = 'img.jpg'

    img_data = imread(img_path)
    img_data = imresize(img_data, (299, 299, 3))
    img_data = img_data.astype(np.float32)
    img_data = np.expand_dims(img_data, 0)

    # print('Starting Session, setting the GPU memory usage to %f' % args.gpu_memory)
    # gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_memory)
    # sess_config = tf.ConfigProto(gpu_options=gpu_options)
    persistent_sess = tf.Session(graph=graph)  # , config=sess_config)

    input_node = graph.get_tensor_by_name('prefix/batch/fifo_queue:0')
    output_node = graph.get_tensor_by_name('prefix/InceptionResnetV2/Logits/Predictions:0')

    predictions = persistent_sess.run(output_node, feed_dict={input_node: [img_data]})
    print(predictions)
    label_predicted = np.argmax(predictions[0])
    print(label_predicted)

错误：

 File /ImageClassification_TransferLearning System/ModelTraining/model/model_frezzing.py", line 96, in <module>
    predictions = persistent_sess.run(output_node, feed_dict={input_node: [img_data]})
  File "\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 895, in run
    run_metadata_ptr)
  File "\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1078, in _run
    subfeed_dtype = subfeed_t.dtype.as_numpy_dtype
  File "\Anaconda3\lib\site-packages\tensorflow\python\framework\dtypes.py", line 122, in as_numpy_dtype
    return _TF_TO_NP[self._type_enum]
KeyError: 20

我发现了问题！！ 我必须从名为：prefix/batch:0的输入op中输入模型

 input_node = graph.get_tensor_by_name('prefix/batch:0')