Python 张量流权矩阵秩误差

Python 张量流权矩阵秩误差,python,python-2.7,tensorflow,convolution,Python,Python 2.7,Tensorflow,Convolution,当我运行代码时,我得到了错误 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(image, 180, 180, 1) resized.set_shape([180,180,3]) flipped_images = tf

当我运行代码时,我得到了错误

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(image, 180, 180, 1)
   resized.set_shape([180,180,3])
   flipped_images = tf.image.flip_up_down(resized)
   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')



image,label = inputs()
W_conv1=weight_variable([5,5,3,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)


W_conv2=weights_variable([5,5,32,64])
b_conv2 = bias_variable([32])
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 * 32, 512])
b_fc1 = bias_variable([512])

h_pool2_flat = tf.reshape(h_pool2, [-1, 8*8*32])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
W_fc2 = weight_variable([512, 10])
b_fc2 = bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))   
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) 

init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
tf.train.start_queue_runners(sess=sess)
for i in xrange(100):
    img,label = sess.run(image)
    print (label)
    train_step.run({img, label, 0.5})
但权重已经初始化,即使在初始化之后,它也会显示为空张量。 文件和标签正在正确读取和传输。
第一个卷积层有一个深度为3的5x5窗口,我想要32个这样的5x5滤波器。因此,W_conv1的形状为[5,5,3,32]。

看起来输入返回一个3d张量,而conv2d需要一个4d张量(第一个维度是批处理idx)-如果您只想运行一个图像,您应该首先将其重塑为[1180180,3]

函数
inputs()
返回一个形状张量
180 x 180 x 3
,但需要一个形状的4维张量
batch\u size x height x width x num\u channels

,您可以通过重塑
图像
张量(例如,使用
image=tf.expand_dims(图像,0)
)来实现这一点。然而,如果你正在训练一个神经网络,你可能会想要批量输入。一种方法是使用:


…然后使用
image\u batch
label\u batch
分别使用
image
label

感谢您的快速回复,我尝试了使用train.batch()方法,但没有成功。我有以下疑问,首先,如果train.batch()方法输出一个张量列表,那么为什么我们要将它分别指定给image\u batch和label\u batch。为什么我们不能分别使用image\u batch[0或1]来访问它们呢。其次,当我在训练期间将image\u batch和label\u batch传递给它们各自的占位符时,我得到以下错误“'Operation'对象不可调用”1。执行
image\u batch,label\u batch=tf.train.batch(…)
相当于
batches=tf.train.batch(…);图像_批次=批次[0];label\u batch=批次[1]
。2.我不确定你在这里做什么来得到这个错误-你可能需要提出另一个问题(但是,您不能将
image\u batch
label\u batch
作为馈送值传递,因为它们是符号张量;现在只支持馈送NumPy数组之类的具体值。相反,您应该使用
image\u batch
label\u batch
作为直接ops的参数,而不需要通过placehol我有一个单独的问题。你能检查一下吗?@mrry
"ValueError: ShapesTensorShape([Dimension(180),Dimension(180),Dimension(3)]) and TensorShape([Dimension(None), Dimension(None), Dimension(None), Dimension(None)]) must have the same rank"
image, label = inputs()

# Set batch_size to the largest value that works for your configuration.
image_batch, label_batch = tf.train.batch([image, label], batch_size=32)