Question

当冻结带有局部变量的图时，freeze_graph出现错误，指出“尝试使用未初始化的值...”。有问题的局部变量是通过以下方式初始化的：

    with tf.variable_scope(tf.get_variable_scope(),reuse=tf.AUTO_REUSE):
        b_init = tf.constant(10.0, shape=[2, 1], dtype="float32",name = 'bi')
        b = tf.get_variable('b',initializer=b_init,collections=[tf.GraphKeys.LOCAL_VARIABLES])

我能够创建一个保存的模型并运行该保存的模型。但是，我试图冻结另一个图进行优化。如果删除“ LOCAL_VARIABLES”标志，此错误将消失。但是，此变量然后变为全局变量，这会导致重新加载我的检查点时出现问题（Tensorflow无法在检查点中找到该变量）。

通常，我希望Frozen_graph使用'b_init'初始化'b'。

重现该问题的代码：

import os, sys, json
import tensorflow as tf
from tensorflow.python.lib.io import file_io

from tensorflow.core.framework import variable_pb2
from tensorflow.python.framework import ops
from tensorflow.python.ops import variables
from tensorflow.python.framework.ops import register_proto_function

from tensorflow.python.saved_model import tag_constants
from tensorflow.python.tools import freeze_graph
from tensorflow.python import ops
from tensorflow.tools.graph_transforms import TransformGraph

#flags
tf.app.flags.DEFINE_integer('model_version',1,'Models version number.')
tf.app.flags.DEFINE_string('export_model_dir','../model_batch/versions', 'Directory where model will be exported to')

FLAGS = tf.app.flags.FLAGS

def main(_):
    ''' main function'''
    a = tf.placeholder(dtype = tf.float32, shape = [2,1])

    with tf.variable_scope(tf.get_variable_scope(),reuse=tf.AUTO_REUSE):
        b_init = tf.constant(10.0, shape=[2, 1], dtype="float32",name = 'bi')
        b = tf.get_variable('b',initializer=b_init,collections=[tf.GraphKeys.LOCAL_VARIABLES])

    b = tf.assign(b,a)
    c = []

    for d in range(5):
        b = b * 1.1

    c.append(b)
    c = tf.identity(c,name = 'c')

    init = tf.group(tf.global_variables_initializer(),
                   tf.local_variables_initializer())

    with tf.Session() as sess:

        #init
        sess.run(init)
        print(tf.get_default_graph().get_collection(tf.GraphKeys.LOCAL_VARIABLES))

        #create saved model builder class
        export_path_base = FLAGS.export_model_dir
        export_path = os.path.join(
            tf.compat.as_bytes(export_path_base),
            tf.compat.as_bytes(str(FLAGS.model_version)))

        if tf.gfile.Exists(export_path):
            print ('Removing previous artifacts')
            tf.gfile.DeleteRecursively(export_path)

        #inputs
        tensor_info_a  = tf.saved_model.utils.build_tensor_info(a)

        #outputs
        tensor_info_c = tf.saved_model.utils.build_tensor_info(c)

        print('Exporting trained model to', export_path)
        builder = tf.saved_model.builder.SavedModelBuilder(export_path)

        #define signatures
        prediction_signature = (
            tf.saved_model.signature_def_utils.build_signature_def(
                inputs={'cameras': tensor_info_a},
                outputs = {'depthmap' : tensor_info_c},
                method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME))

        builder.add_meta_graph_and_variables(
            sess, [tf.saved_model.tag_constants.SERVING],
            signature_def_map = {'predict_batch': prediction_signature})

        #export model
        builder.save(as_text=True)

        writer = tf.summary.FileWriter("output_batch", sess.graph)
        writer.close()

    #load graph from saved model
    print ('Freezing graph')
    initializer_nodes = ''
    output_node_names = 'c'
    saved_model_dir = os.path.join(FLAGS.export_model_dir,str(FLAGS.model_version))
    output_graph_filename = os.path.join(saved_model_dir,'frozen_graph.pb')

    freeze_graph.freeze_graph(
        input_saved_model_dir=saved_model_dir,
        output_graph=output_graph_filename,
        saved_model_tags = tag_constants.SERVING,
        output_node_names=output_node_names,
        initializer_nodes=initializer_nodes,
        input_graph=None,
        input_saver=False,
        input_binary=False,
        input_checkpoint=None,
        restore_op_name=None,
        filename_tensor_name=None,
        clear_devices=False)

if __name__ == '__main__':
    tf.app.run()

Answer 1

我无法在冻结的图形中包含local_variables，但是我确实提出了解决方案。

最初的问题是我的检查点是从包含local_variables的图形创建的。不幸的是，冻结图形会产生错误：

Attempting to use uninitialized value...

要解决此问题，我所做的就是将局部变量更改为不可训练的全局变量。然后，使用以下解决方案过滤掉不在检查点中的全局变量：

https://stackoverflow.com/a/39142780/6693924

我能够创建一个saveModel并冻结其图形。

Tensorflow Frozen_graph无法初始化local_variables

1 个答案: