我整天都在解决这个问题，但无法在网上找到可能的解决方案。
我正在编码一个卷积神经网络以对一些BW图像进行分类。我首先读取数据，准备网络的体系结构，然后运行训练部分，但是在尝试训练的过程中，我始终会遇到此错误：
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected begin[0] == 0 (got -1) and size[0] == 0 (got 1) when input.dim_size(0) == 0
[[Node: Slice_1 = Slice[Index=DT_INT32, T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](Shape_2, Slice_1/begin, Slice_1/size)]]
我在网上找不到任何有用的信息。而且我不知道出什么问题了。非常感谢你们，我在下面链接了整个代码：
import tensorflow as tf
from tensorflow.python.framework import ops
from tensorflow.python.framework import dtypes
import random
"""
N_CLASSES, number of classes of the dataset, 2 classes, one for an error and the other one if it is ok
BATH SIZE, is going to depend on the number of samples taht we have
IMAGE_HEIGHT, height of the images
IMAGE_WIDTH, width of the images
TOTAL_SIZE, total size of the image
"""
N_CLASSES = 2
BATCH_SIZE = 5
NUM_CHANNELS = 1
IMAGE_HEIGHT = 696
IMAGE_WIDTH = 1024
TOTAL_SIZE = 1024*696
x = tf.placeholder(tf.float32, [None, None, 1])
y = tf.placeholder(tf.int32)
# Keep rate will do 0.6
keep_rate = 0.6
keep_prob = tf.placeholder(tf.float32)
""" Function for encoding the label from string to int"""
def encode_label(label):
return int(label)
""" Function for reading a label file separeted by ,
F.E: /home/pacocp/dataset/image1.jpg,1
"""
def read_label_file(file):
f = open(file)
filepaths = []
labels = []
for line in f:
filepath, label = line.split(",")
filepaths.append(filepath)
labels.append(encode_label(label))
return filepaths, labels
"""This function is going to load the SEM images """
def load_images(dataset_path,test_labels_file,train_labels_file):
# reading labels and file path
train_filepaths, train_labels = read_label_file(dataset_path + train_labels_file)
test_filepaths, test_labels = read_label_file(dataset_path + test_labels_file)
"""
# transform relative path into full path
train_filepaths = [ dataset_path + fp for fp in train_filepaths]
test_filepaths = [ dataset_path + fp for fp in test_filepaths]
"""
# for this example we will create or own test partition
all_filepaths = train_filepaths + test_filepaths
all_labels = train_labels + test_labels
# convert string into tensors
all_images = ops.convert_to_tensor(all_filepaths, dtype=dtypes.string)
all_labels = ops.convert_to_tensor(all_labels, dtype=dtypes.int32)
#now, we are going to create a partition vector
test_set_size = 5
partitions = [0] * len(all_filepaths)
partitions[:test_set_size] = [1] * test_set_size
random.shuffle(partitions)
# partition our data into a test and train set according to our partition vector
train_images, test_images = tf.dynamic_partition(all_images, partitions, 2)
train_labels, test_labels = tf.dynamic_partition(all_labels, partitions, 2)
# create input queues
train_input_queue = tf.train.slice_input_producer(
[train_images, train_labels],
shuffle=False)
test_input_queue = tf.train.slice_input_producer(
[test_images, test_labels],
shuffle=False)
# process path and string tensor into an image and a label
file_content = tf.read_file(train_input_queue[0])
train_image = tf.image.decode_jpeg(file_content, channels=NUM_CHANNELS) #You have to change this line depending on the image format
train_label = train_input_queue[1]
file_content = tf.read_file(test_input_queue[0])
test_image = tf.image.decode_jpeg(file_content, channels=NUM_CHANNELS)
test_label = test_input_queue[1]
# define tensor shape
train_image.set_shape([IMAGE_HEIGHT,IMAGE_WIDTH,1])
test_image.set_shape([IMAGE_HEIGHT,IMAGE_WIDTH,1])
""" TEST FOR NOT USING BATCHES AND USING ALL THE IMAGES DIRECTLY
print("Here")
# collect batches of images before processing
train_image_batch, train_label_batch = tf.train.batch(
[train_image, train_label],
batch_size=BATCH_SIZE
#,num_threads=1
)
test_image_batch, test_label_batch = tf.train.batch(
[test_image, test_label],
batch_size=BATCH_SIZE
#,num_threads=1
)
return {'train_image_batch':train_image_batch, 'train_label_batch':train_label_batch,
'test_image_batch':test_image_batch, 'test_label_batch':test_label_batch}
"""
return {'train_image_batch':train_image, 'train_label_batch':train_label,
'test_image_batch':test_image, 'test_label_batch':test_label}
""" This is going to be used for creating the weights and the biases"""
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(data, weights):
return tf.nn.conv2d(data, weights, strides=[1,1,1,1], padding='SAME') # We are not going to get the depth
def maxpool2d(data):
"""Here we are going to move two by two at a time size of the window movement of the window"""
return tf.nn.max_pool(data, ksize=[1,2,2,1],strides=[1,2,2,1], padding = 'SAME')
def convolutional_neural_network(data):
"""Here we are going to create the weights and biases variables for generating our neural network"""
print("Creating first layer")
w_conv1 = weight_variable([15, 15, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(data, shape=[-1, 696, 1024, 1]) #Reshape the image, second and third elements
# are height and width, an the third dimension the colors channel
#First convolutional layer
h_conv1 = tf.nn.relu(conv2d(x_image,w_conv1 + b_conv1))
h_pool1 = maxpool2d(h_conv1)
print("Creating second layer")
w_conv2 = weight_variable([15, 15, 32, 64])
b_conv2 = bias_variable([64])
#Second convolutional layer
h_conv2 = tf.nn.relu(conv2d(h_pool1,w_conv2 + b_conv2))
h_pool2 = maxpool2d(h_conv2)
print("Craeating fully-conected layer")
w_fc1 = weight_variable([1024, 1024])
b_fc1 = bias_variable([1024])
#Final
h_pool2_flat = tf.reshape(h_pool2,[-1,1024])
fc = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1 )+ b_fc1)
"""The idea of dropout is for help us in a
bigger neural network, dropout is going to help fight
local minimuns"""
fc_dropout = tf.nn.dropout(fc, keep_rate) #Compute dropout
print("Creating output layer")
w_fc2 = weight_variable([1024, N_CLASSES])
b_fc2 = bias_variable([N_CLASSES])
#Final layer with a softmax
y = tf.matmul(fc_dropout, w_fc2)+ b_fc2
print("CNN created")
return y
'''Here is the main where we are going to train the convolutional neural network'''
#Here we read the images
dataset_path = "/media/datos/Dropbox/4ºaño/Image Analysis and Computer Vision/NanoFibers/DataSet/"
test_labels_file = "SEM_test_labels.txt"
train_labels_file = "SEM_train_labels.txt"
print("Loading the images...")
train_and_test_sets = load_images(dataset_path,test_labels_file,train_labels_file)
print("Images loaded sucessfully!")
#Now, I'm going to save some things in variables for a clearer code
train_image_batch = train_and_test_sets['train_image_batch']
train_label_batch = train_and_test_sets['train_label_batch']
test_image_batch = train_and_test_sets['test_image_batch']
test_label_batch = train_and_test_sets['test_label_batch']
"""THIS IS FOR SHOWING THE SETS, JUST FOR DEBBUGING
with tf.Session() as sess:
# initialize the variables
sess.run(tf.global_variables_initializer())
# initialize the queue threads to start to shovel data
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
print("from the train set:")
for i in range(31):
print(sess.run(train_image_batch))
print("from the test set:")
for i in range(11):
print(sess.run(test_label_batch))
# stop our queue threads and properly close the session
coord.request_stop()
coord.join(threads)
sess.close()
"""
sess = tf.Session()
#Now, I'm going to save some things in variables for a clearer code
train_image_batch = train_and_test_sets['train_image_batch']
train_label_batch = train_and_test_sets['train_label_batch']
test_image_batch = train_and_test_sets['test_image_batch']
test_label_batch = train_and_test_sets['test_label_batch']
sess = tf.InteractiveSession()
#Firstly we get the prediction
prediction = convolutional_neural_network(x)
#Cross Entropy is what we are going to try to reduce
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction, y))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(prediction,1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
#----------PROBLEM HERE
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)
# Here it's where the train it's going to be made
train_images = sess.run(train_image_batch)
train_labels = sess.run(train_label_batch)
test_images = sess.run(test_image_batch)
test_labels = sess.run(test_label_batch)
with sess.as_default():
index_for_batch = 1
for i in range(50):
print("generating batches")
#batch_image = train_image_batch[index_for_batch].eval(session=sess)
#batch_label = train_label_batch[index_for_batch].eval(session=sess)
print("generated")
if (i%5 == 0) and (i != 0):
train_accuracy = accuracy.eval(feed_dict={
x:train_images, y: train_labels, keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
print("*********Doing training step***********")
train_step.run(feed_dict={x: train_images, y: train_labels, keep_prob: 0.5})
if(index_for_batch + 1 > len(train_image_batch)):
index_for_batch = 1
else:
index_for_batch = index_for_batch + 1
#Here we are gong to test the accuracy of the training
print("test accuracy %g"%accuracy.eval(feed_dict={
x: test_images, y: test_labels, keep_prob: 1.0}))
OPS名称编辑错误
Traceback (most recent call last):
File "/usr/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1021, in _do_call
return fn(*args)
File "/usr/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1003, in _run_fn
status, run_metadata)
File "/usr/lib/python3.5/contextlib.py", line 66, in __exit__
next(self.gen)
File "/usr/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 469, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected begin[0] == 0 (got -1) and size[0] == 0 (got 1) when input.dim_size(0) == 0
[[Node: Slice_1 = Slice[Index=DT_INT32, T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](Shape_2, Slice_1/begin, Slice_1/size)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "convolutional_net.py", line 295, in <module>
train_step.run(feed_dict={x: train_images, y: train_labels, keep_prob: 0.5})
File "/usr/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1449, in run
_run_using_default_session(self, feed_dict, self.graph, session)
File "/usr/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3668, in _run_using_default_session
session.run(operation, feed_dict)
File "/usr/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 766, in run
run_metadata_ptr)
File "/usr/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 964, in _run
feed_dict_string, options, run_metadata)
File "/usr/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1014, in _do_run
target_list, options, run_metadata)
File "/usr/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1034, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Expected begin[0] == 0 (got -1) and size[0] == 0 (got 1) when input.dim_size(0) == 0
[[Node: Slice_1 = Slice[Index=DT_INT32, T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](Shape_2, Slice_1/begin, Slice_1/size)]]
Caused by op 'Slice_1', defined at:
File "convolutional_net.py", line 264, in <module>
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction, y))
File "/usr/lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 1443, in softmax_cross_entropy_with_logits
labels = _flatten_outer_dims(labels)
File "/usr/lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 1245, in _flatten_outer_dims
array_ops.shape(logits), [math_ops.sub(rank, 1)], [1])
File "/usr/lib/python3.5/site-packages/tensorflow/python/ops/array_ops.py", line 484, in slice
return gen_array_ops._slice(input_, begin, size, name=name)
File "/usr/lib/python3.5/site-packages/tensorflow/python/ops/gen_array_ops.py", line 2868, in _slice
name=name)
File "/usr/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/usr/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1128, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Expected begin[0] == 0 (got -1) and size[0] == 0 (got 1) when input.dim_size(0) == 0
[[Node: Slice_1 = Slice[Index=DT_INT32, T=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](Shape_2, Slice_1/begin, Slice_1/size)]]
最佳答案
通过阅读代码，问题源于tf.nn.softmax_cross_entropy_with_logits()的参数形状。根据文档：
logits和labels必须具有相同的形状[batch_size, num_classes]和相同的dtype（float16，float32或float64）。
您的代码调用tf.nn.softmax_cross_entropy_with_logits(prediction, y)，因此让我们看一下参数的形状：prediction是从convolutional_neural_network(x)返回的值，其形状为[batch_size, N_CLASSES]。 （x的占位符将batch_size表示为None，因此它可以是动态的。）y被定义为y = tf.placeholder(tf.int32)。占位符没有形状信息，因此它在静态上是未知的（部分解释了错误的错误消息...有关此内容的更多信息，请参见下文）。为了找出y的实际形状，我们可以看一下如何填充占位符，并且看起来它是从输入文件中解析出的整数列表的来源，其中整数代表对应的真实标签例。
要解决此问题，应将tf.nn.softmax_cross_entropy_with_logits()替换为其稀疏的副本tf.nn.sparse_softmax_cross_entropy_with_logits()，该副本可以处理您使用的格式的输入数据：
cross_entropy = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(prediction, y))
（另一种方法是使用
tf.one_hot(y, N_CLASSES)将y转换为tf.nn.softmax_cross_entropy_with_logits()的适当的一键编码，但是效率可能较低，因为它必须为目标值实现一个可能较大的矩阵。）请注意，您收到此问题的运行时错误的原因是因为
tf.placeholder()的y的定义方式（没有静态形状）。如果将其定义为向量，则在图构建时会出现错误：# `y` is a (variable-length) vector.
y = tf.placeholder(tf.int32, shape=[None])
关于python - 制作train_step.run()时出现Tensorflow错误，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/41618564/