Python Tensorflow错误“;形状张量形状()必须具有秩1“;
我试图在我自己的[32x32x3]维图像上运行tensorflow卷积模型。在培训期间,正确读取图像并将其分配给占位符。运行列车步骤op时出现问题。当我执行图形时,我得到以下错误Python Tensorflow错误“;形状张量形状()必须具有秩1“;,python,tensorflow,Python,Tensorflow,我试图在我自己的[32x32x3]维图像上运行tensorflow卷积模型。在培训期间,正确读取图像并将其分配给占位符。运行列车步骤op时出现问题。当我执行图形时,我得到以下错误 import tensorflow as tf import numpy as np import os from PIL import Image cur_dir = os.getcwd() def modify_image(image): #resized = tf.image.resize_images(i
import tensorflow as tf
import numpy as np
import os
from PIL import Image
cur_dir = os.getcwd()
def modify_image(image):
#resized = tf.image.resize_images(image, 180, 180, 3)
image.set_shape([32,32,3])
flipped_images = tf.image.flip_up_down(image)
return flipped_images
def read_image(filename_queue):
reader = tf.WholeFileReader()
key,value = reader.read(filename_queue)
image = tf.image.decode_jpeg(value)
return key,image
def inputs():
filenames = ['standard_1.jpg', 'standard_2.jpg' ]
filename_queue = tf.train.string_input_producer(filenames)
filename,read_input = read_image(filename_queue)
reshaped_image = modify_image(read_input)
reshaped_image = tf.cast(reshaped_image, tf.float32)
label=tf.constant([1])
return reshaped_image,label
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(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
x = tf.placeholder(tf.float32, shape=[None,32,32,3])
y_ = tf.placeholder(tf.float32, shape=[None, 1])
image,label=inputs()
image=tf.reshape(image,[-1,32,32,3])
label=tf.reshape(label,[-1,1])
image_batch=tf.train.batch([image],batch_size=2)
label_batch=tf.train.batch([label],batch_size=2)
W_conv1 = weight_variable([5, 5, 3, 32])
b_conv1 = bias_variable([32])
image_4d=x_image = tf.reshape(image, [-1,32,32,3])
h_conv1 = tf.nn.relu(conv2d(image_4d, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
W_fc1 = weight_variable([8 * 8 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 8*8*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 2])
b_fc2 = bias_variable([2])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy= -tf.reduce_sum(tf.cast(image_batch[1],tf.float32)*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
for i in range(20000):
sess.run(train_step,feed_dict={x:image_batch[0:1],y_:label_batch[0:1]})
但是当我看到这个例子时,图像只是以[batch_size,height,width,depth]张量的形式出现的。这个例子很好用。
我遗漏了什么吗?我认为错误来自这一行:
TensorShape([Dimension(2), Dimension(1), Dimension(32), Dimension(32), Dimension(3)]) must have rank 1
image\u batch
是一个5维张量,形状为[2,1,32,32,3]
,其中2是tf.train.batch()
的batch\u size
参数,1是由前面的image=tf.reformate(image,[-1,32,3])
添加的。(N.B.由于tf.train.batch()
已经添加了一个批维度,并且在以后构建image_4d
时,您必须撤消重塑的效果,因此此重塑是不必要的)
在TensorFlow中,切片操作(即image\u batch[1]
)的灵活性略低于NumPy。切片中指定的维度数量必须等于张量的秩:即,必须指定所有五个维度才能使其工作。您可以指定image\u batch[1,:,:,:,:,:]
来获取image\u batch
的4-D切片
但是,我注意到您的计划中还有一些其他问题:
x
和y
在您的程序中未使用。此外,您似乎正在输入一个tf.Tensor
(实际上是image\u batch
的非法切片),因此在执行该语句时,这将失败。如果您打算使用feed,那么应该输入保存输入数据的NumPy数组tf.WholeFileReader
,则需要调用tf.train.start\u queue\u runners()
开始。否则,您的程序将挂起,等待输入这个问题仍然很有用,但包含的代码比演示问题所需的代码要多得多——现在很难将其缩减为仅失败的切片操作,因为答案解决了与所问问题无关的已发布代码的其他位。下次请把你的代码精简到一个最小的例子;这不需要8行就可以复制,更不用说80行了。
cross_entropy= -tf.reduce_sum(tf.cast(image_batch[1],tf.float32)*tf.log(y_conv))