从logits和checkpoint训练模型

Question

我是张量流的新手，我正在尝试训练移动net_v1。为此，我首先从txt文件创建了多类的tfrecords文件。（例如：namefile label1 label2 ...）

import sys, os
import tensorflow as tf 
import cv2
import numpy as np
import matplotlib.pyplot as plt
# function

def load_image(addr):
    # read an image and resize to (224, 224)
    # cv2 load images as BGR, convert it to RGB
    img = cv2.imread(addr)
    img = cv2.resize(img, (224, 224), interpolation=cv2.INTER_CUBIC)
    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    img = img.astype(np.float32)
    return img

def _int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[*value]))

def _bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

def loadData(inputs):
    addrs = []
    labels = []
    f = open(inputs, 'r')
    data = [ln.split(' ') for ln in f ]
    f.close()
    print(data)
    for i in range(0, len(data)):
        addrs.append(data[i][0].rstrip())
        l = []
        for j in range(1,len(data[i])):
            if(data[i][j].rstrip().isdigit() == True):
                l.append(int(data[i][j].rstrip()))

        print(l)
        labels.append(l)

    return addrs, labels

def CreateTrainFile(input_filename, train_filename,):
    path = '/home/rd/Documents/RD2/Databases/Faces/'
    # load file and label
    train_addrs, train_labels = loadData(input_filename)
    print(train_labels)
    # open the TFRecords file
    writer = tf.python_io.TFRecordWriter(train_filename)
    for i in range(len(train_addrs)):
        # print how many images are saved every 1000 images
        if not i % 1000:
            print('Train data: {}/{}'.format(i, len(train_addrs)))
            sys.stdout.flush()
        # Load the image
        img = load_image(train_addrs[i])
        label = train_labels[i]
        print('label : ', _int64_feature(label))
        # Create a feature
        feature = {'train/label': _int64_feature(label),
                'train/image': _bytes_feature(tf.compat.as_bytes(img.tostring()))}
        # Create an example protocol buffer
        example = tf.train.Example(features=tf.train.Features(feature=feature))

        # Serialize to string and write on the file
        writer.write(example.SerializeToString())

    writer.close()
    sys.stdout.flush()

# open the TFRecords file
def CreateValidationFile(val_filename):

    writer = tf.python_io.TFRecordWriter(val_filename)
    for i in range(len(val_addrs)):
        # print how many images are saved every 1000 images
        if not i % 1000:
            print('Val data: {}/{}'.format(i, len(val_addrs)))
            sys.stdout.flush()
        # Load the image
        img = load_image(val_addrs[i])
        label = val_labels[i]
        # Create a feature
        feature = {'val/label': _int64_feature(label),
                'val/image': _bytes_feature(tf.compat.as_bytes(img.tostring()))}
        # Create an example protocol buffer
        example = tf.train.Example(features=tf.train.Features(feature=feature))
        # Serialize to string and write on the file
        writer.write(example.SerializeToString())
    writer.close()
    sys.stdout.flush()

# open the TFRecords file
def CreateTestFile(test_filename):
    writer = tf.python_io.TFRecordWriter(test_filename)
    for i in range(len(test_addrs)):
        # print how many images are saved every 1000 images
        if not i % 1000:
            print('Test data: {}/{}'.format(i, len(test_addrs)))
            sys.stdout.flush()
        # Load the image
        img = load_image(test_addrs[i])
        label = test_labels[i]
        # Create a feature
        feature = {'test/label': _int64_feature(label),
                'test/image': _bytes_feature(tf.compat.as_bytes(img.tostring()))}
        # Create an example protocol buffer
        example = tf.train.Example(features=tf.train.Features(feature=feature))
        # Serialize to string and write on the file
        writer.write(example.SerializeToString())
    writer.close()
    sys.stdout.flush()

def ReadRecordFileTrain(data_path):
    #data_path = 'train.tfrecords'  # address to save the hdf5 file
    with tf.Session() as sess:
        feature = {'train/image': tf.FixedLenFeature([], tf.string),
                'train/label': tf.FixedLenFeature([], tf.int64)}
        # Create a list of filenames and pass it to a queue
        filename_queue = tf.train.string_input_producer([data_path], num_epochs=1)
        # Define a reader and read the next record
        reader = tf.TFRecordReader()
        _, serialized_example = reader.read(filename_queue)
        # Decode the record read by the reader
        features = tf.parse_single_example(serialized_example, features=feature)
        # Convert the image data from string back to the numbers
        image = tf.decode_raw(features['train/image'], tf.float32)

        # Cast label data into int32
        label = tf.cast(features['train/label'], tf.int32)
        # Reshape image data into the original shape
        image = tf.reshape(image, [224, 224, 3])

        # Any preprocessing here ...

        # Creates batches by randomly shuffling tensors
        images, labels = tf.train.shuffle_batch([image, label], batch_size=2, capacity=30, num_threads=1, min_after_dequeue=10)
        return images, labels
def main():
    train_filename = 'train.tfrecords'  # address to save the TFRecords file
    #test_filename = 'test.tfrecords'  # address to save the TFRecords file
    #val_filename = 'val.tfrecords'  # address to save the TFRecords file
    CreateTrainFile("data.txt", train_filename)
main()

并阅读tf记录：

def ReadRecordFileTrain(data_path):
    #data_path = 'train.tfrecords'  # address to save the hdf5 file
    with tf.Session() as sess:
        feature = {'train/image': tf.FixedLenFeature([], tf.string),
                'train/label': tf.FixedLenFeature([2], tf.int64)}
        # Create a list of filenames and pass it to a queue
        filename_queue = tf.train.string_input_producer([data_path], num_epochs=1)
        # Define a reader and read the next record
        reader = tf.TFRecordReader()
        _, serialized_example = reader.read(filename_queue)
        # Decode the record read by the reader
        features = tf.parse_single_example(serialized_example, features=feature)
        # Convert the image data from string back to the numbers
        image = tf.decode_raw(features['train/image'], tf.float32)
        print('label1 :', features['train/label'] )
        # Cast label data into int32
        label = tf.cast(features['train/label'], tf.int32)
        print('label load:', label)
        # Reshape image data into the original shape
        image = tf.reshape(image, [224, 224, 3])

        # Any preprocessing here ...

        # Creates batches by randomly shuffling tensors
        images, labels = tf.train.batch([image, label], batch_size=2, capacity=30, num_threads=1)
        return images, labels

我认为它有效，但我不确定（当我调用这些函数时，我没有任何错误。） 然后，我加载模型及其重量。调用损失函数并尝试开始训练，但此时它失败了。

g = tf.Graph()
with g.as_default():
    # size of the folder
    inputs = tf.placeholder(tf.float32, [1, 224, 224, 3])

    # load dataset
    images, labels = ReadRecordFileTrain('train.tfrecords')
    print('load dataset done')
    print('labels = ', labels)
    print('data = ', images)
    print(tf.shape(labels))

    # load network
    network, end_points= mobilenet.mobilenet_v1(images, num_classes=2, depth_multiplier=0.25 )

    print('load network done')
    print('network : ', network)

    variables_to_restore = slim.get_variables_to_restore(exclude=["MobilenetV1/Logits/Conv2d_1c_1x1"])

    load_checkpoint = "modele_mobilenet_v1_025/mobilenet_v1_0.25_224.ckpt"
    init_fn = slim.assign_from_checkpoint_fn(load_checkpoint, variables_to_restore)
    print('custom network done')



    # Specify the loss function:
    tf.losses.softmax_cross_entropy(labels, network)

    total_loss = tf.losses.get_total_loss()
    #tf.scalar_summary('losses/total_loss', total_loss)

    # Specify the optimization scheme:
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=.001)

    # create_train_op that ensures that when we evaluate it to get the loss,
    # the update_ops are done and the gradient updates are computed.
    train_tensor = slim.learning.create_train_op(total_loss, optimizer)
    print('loss and optimizer chosen')
    # Actually runs training.
    save_checkpoint = 'model/modelcheck'

    # start training
    learning = slim.learning.train(train_tensor, save_checkpoint, init_fn=init_fn, number_of_steps=1000)

错误消息：

label1 : Tensor("ParseSingleExample/Squeeze_train/label:0", shape=(2,), dtype=int64)
label load: Tensor("Cast:0", shape=(2,), dtype=int32)
load dataset done
labels =  Tensor("batch:1", shape=(2, 2), dtype=int32)
data =  Tensor("batch:0", shape=(2, 224, 224, 3), dtype=float32)
Tensor("Shape:0", shape=(2,), dtype=int32)
load network done
network :  Tensor("MobilenetV1/Logits/SpatialSqueeze:0", shape=(2, 2), dtype=float32)
custom network done
loss and optimizer chosen
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1039, in _do_call
    return fn(*args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1021, in _run_fn
    status, run_metadata)
File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [1,1,256,2] rhs shape= [1,1,256,1]
    [[Node: save_1/Assign_109 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV1/Logits/Conv2d_1c_1x1/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/cpu:0"](MobilenetV1/Logits/Conv2d_1c_1x1/weights, save_1/RestoreV2_109)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "test.py", line 106, in <module>
    main()
File "test.py", line 103, in main
    learning = slim.learning.train(train_tensor, save_checkpoint, init_fn=init_fn, number_of_steps=1000)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/slim/python/slim/learning.py", line 725, in train
    master, start_standard_services=False, config=session_config) as sess:
File "/usr/lib/python3.5/contextlib.py", line 59, in __enter__
    return next(self.gen)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/supervisor.py", line 960, in managed_session
    self.stop(close_summary_writer=close_summary_writer)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/supervisor.py", line 788, in stop
    stop_grace_period_secs=self._stop_grace_secs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/coordinator.py", line 389, in join
    six.reraise(*self._exc_info_to_raise)
File "/usr/lib/python3/dist-packages/six.py", line 686, in reraise
    raise value
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/supervisor.py", line 949, in managed_session
    start_standard_services=start_standard_services)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/supervisor.py", line 706, in prepare_or_wait_for_session
    init_feed_dict=self._init_feed_dict, init_fn=self._init_fn)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/session_manager.py", line 256, in prepare_session
    config=config)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/session_manager.py", line 188, in _restore_checkpoint
    saver.restore(sess, ckpt.model_checkpoint_path)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1457, in restore
    {self.saver_def.filename_tensor_name: save_path})
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 778, in run
    run_metadata_ptr)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 982, in _run
    feed_dict_string, options, run_metadata)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1032, in _do_run
    target_list, options, run_metadata)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1052, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [1,1,256,2] rhs shape= [1,1,256,1]
    [[Node: save_1/Assign_109 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV1/Logits/Conv2d_1c_1x1/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/cpu:0"](MobilenetV1/Logits/Conv2d_1c_1x1/weights, save_1/RestoreV2_109)]]

Caused by op 'save_1/Assign_109', defined at:
File "test.py", line 106, in <module>
    main()
File "test.py", line 103, in main
    learning = slim.learning.train(train_tensor, save_checkpoint, init_fn=init_fn, number_of_steps=1000)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/slim/python/slim/learning.py", line 642, in train
    saver = saver or tf_saver.Saver()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1056, in __init__
    self.build()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1086, in build
    restore_sequentially=self._restore_sequentially)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 691, in build
    restore_sequentially, reshape)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 419, in _AddRestoreOps
    assign_ops.append(saveable.restore(tensors, shapes))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 155, in restore
    self.op.get_shape().is_fully_defined())
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/state_ops.py", line 270, in assign
    validate_shape=validate_shape)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_state_ops.py", line 47, in assign
    use_locking=use_locking, name=name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
    op_def=op_def)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
    original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [1,1,256,2] rhs shape= [1,1,256,1]
    [[Node: save_1/Assign_109 = Assign[T=DT_FLOAT, _class=["loc:@MobilenetV1/Logits/Conv2d_1c_1x1/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/cpu:0"](MobilenetV1/Logits/Conv2d_1c_1x1/weights, save_1/RestoreV2_109)]]

我不明白问题的来源以及解决方法。

Answer 1

  

InvalidArgumentError：Assign要求两个张量的形状匹配。   lhs shape = [1,1,256,2] rhs shape = [1,1,256,1]

当模型目录中保存的模型与我当前运行的模型发生冲突时，我常常遇到此错误。尝试删除您的模型目录并重新开始培训。

Answer 2

似乎解决了错误，但现在，当我想用​​tf.Session执行它时，它失败了。我想知道问题是来自我的图表还是我在tf.Session中做错了什么？

def evaluation(logits, labels):

    with tf.name_scope('Accuracy'):
# Operation comparing prediction with true label
        correct_prediction = tf.equal(tf.argmax(logits,1), tf.argmax(labels, 1))

# Operation calculating the accuracy of the predictions
        accuracy =  tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

# Summary operation for the accuracy
#tf.scalar_summary('train_accuracy', accuracy)
        return accuracy


g = tf.Graph()
with g.as_default():
    # size of the folder
    inputs = tf.placeholder(tf.float32, [1, 224, 224, 3])

    # load dataset
    images, labels = ReadRecordFileTrain('train.tfrecords')
    print('load dataset done')
    print('labels = ', labels)
    print('data = ', images)
    print(tf.shape(labels))

    # load network
    network, end_points= mobilenet.mobilenet_v1(images, num_classes=2, depth_multiplier=0.25 )

    print('load network done')
    print('network : ', network)

    variables_to_restore = slim.get_variables_to_restore(exclude=["MobilenetV1/Logits/Conv2d_1c_1x1"])

    load_checkpoint = "modele_mobilenet_v1_025/mobilenet_v1_0.25_224.ckpt"
    init_fn = slim.assign_from_checkpoint_fn(load_checkpoint, variables_to_restore)
    print('custom network done')



    # Specify the loss function:
    tf.losses.softmax_cross_entropy(labels, network)

    total_loss = tf.losses.get_total_loss()
    #tf.scalar_summary('losses/total_loss', total_loss)

    # Specify the optimization scheme:
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=.001)

    # create_train_op that ensures that when we evaluate it to get the loss,
    # the update_ops are done and the gradient updates are computed.
    train_tensor = slim.learning.create_train_op(total_loss, optimizer)
    print('loss and optimizer chosen')
    # Actually runs training.
    save_checkpoint = 'model/modelcheck'

    # start training
    learning = slim.learning.train(train_tensor, save_checkpoint, init_fn=init_fn, number_of_steps=1000)

    accuracy = evaluation(network, labels)


with tf.Session(graph=g) as sess:
    sess.run(network)
    print('network load')
    sess.run(total_loss)
    sess.run(accuracy)
    sess.run(train_tensor)
    sess.run(learning)

错误：

label1 : Tensor("ParseSingleExample/Squeeze_train/label:0", shape=(2,), dtype=int64)
label load: Tensor("Cast:0", shape=(2,), dtype=int32)
load dataset done
labels =  Tensor("batch:1", shape=(4, 2), dtype=int32)
data =  Tensor("batch:0", shape=(4, 224, 224, 3), dtype=float32)
Tensor("Shape:0", shape=(2,), dtype=int32)
load network done
network :  Tensor("MobilenetV1/Logits/SpatialSqueeze:0", shape=(4, 2), dtype=float32)
custom network done
loss and optimizer chosen
end of graph
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1039, in _do_call
    return fn(*args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1021, in _run_fn
    status, run_metadata)
File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
    next(self.gen)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta
    [[Node: MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta/read = Identity[T=DT_FLOAT, _class=["loc:@MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta"], _device="/job:localhost/replica:0/task:0/cpu:0"](MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "test.py", line 113, in <module>
    main()
File "test.py", line 105, in main
    sess.run(network)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 778, in run
    run_metadata_ptr)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 982, in _run
    feed_dict_string, options, run_metadata)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1032, in _do_run
    target_list, options, run_metadata)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1052, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta
    [[Node: MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta/read = Identity[T=DT_FLOAT, _class=["loc:@MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta"], _device="/job:localhost/replica:0/task:0/cpu:0"](MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta)]]

Caused by op 'MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta/read', defined at:
File "test.py", line 113, in <module>
    main()
File "test.py", line 67, in main
    network, end_points= mobilenet.mobilenet_v1(images, num_classes=2, depth_multiplier=0.25 )
File "/home/rd/Documents/RD2/users/Ludovic/tensorflow_mobilenet/mobilenet_v1.py", line 301, in mobilenet_v1
    conv_defs=conv_defs)
File "/home/rd/Documents/RD2/users/Ludovic/tensorflow_mobilenet/mobilenet_v1.py", line 228, in mobilenet_v1_base
    scope=end_point)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
    return func(*args, **current_args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1891, in separable_convolution2d
    outputs = normalizer_fn(outputs, **normalizer_params)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
    return func(*args, **current_args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 528, in batch_norm
    outputs = layer.apply(inputs, training=is_training)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/base.py", line 320, in apply
    return self.__call__(inputs, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/base.py", line 286, in __call__
    self.build(input_shapes[0])
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/normalization.py", line 125, in build
    trainable=True)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 1049, in get_variable
    use_resource=use_resource, custom_getter=custom_getter)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 948, in get_variable
    use_resource=use_resource, custom_getter=custom_getter)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 349, in get_variable
    validate_shape=validate_shape, use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 1389, in wrapped_custom_getter
    *args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/base.py", line 275, in variable_getter
    variable_getter=functools.partial(getter, **kwargs))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/layers/base.py", line 228, in _add_variable
    trainable=trainable and self.trainable)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 1389, in wrapped_custom_getter
    *args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1334, in layer_variable_getter
    return _model_variable_getter(getter, *args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1326, in _model_variable_getter
    custom_getter=getter, use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
    return func(*args, **current_args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/variables.py", line 262, in model_variable
    use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
    return func(*args, **current_args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/variables.py", line 217, in variable
    use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1334, in layer_variable_getter
    return _model_variable_getter(getter, *args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1326, in _model_variable_getter
    custom_getter=getter, use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
    return func(*args, **current_args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/variables.py", line 262, in model_variable
    use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 181, in func_with_args
    return func(*args, **current_args)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/framework/python/ops/variables.py", line 217, in variable
    use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 341, in _true_getter
    use_resource=use_resource)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variable_scope.py", line 714, in _get_single_variable
    validate_shape=validate_shape)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variables.py", line 197, in __init__
    expected_shape=expected_shape)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/variables.py", line 316, in _init_from_args
    self._snapshot = array_ops.identity(self._variable, name="read")
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 1338, in identity
    result = _op_def_lib.apply_op("Identity", input=input, name=name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
    op_def=op_def)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
    original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
    self._traceback = _extract_stack()

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta
    [[Node: MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta/read = Identity[T=DT_FLOAT, _class=["loc:@MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta"], _device="/job:localhost/replica:0/task:0/cpu:0"](MobilenetV1/Conv2d_3_depthwise/BatchNorm/beta)]]