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})
当我运行代码时,我收到错误
"ValueError: ShapesTensorShape([Dimension(180),Dimension(180),Dimension(3)]) and TensorShape([Dimension(None), Dimension(None), Dimension(None), Dimension(None)]) must have the same rank"
但权重已经初始化,即便如此,它也显示为空张量。 正在读取和传输文件和标签。 第一个卷积层有一个5x5窗口,深度为3,我希望有32个这样的5X5滤镜。因此W_conv1的形状为[5,5,3,32]。
答案 0 :(得分:2)
inputs()
函数返回形状180 x 180 x 3
的张量,但tf.nn.conv2d()
期望形状为batch_size x height x width x num_channels
的4-D张量。
As etarion suggests,您可以通过重塑image
张量(例如使用image = tf.expand_dims(image, 0)
)来完成此工作。但是,如果您正在训练神经网络,您可能希望批量输入。一种方法是使用tf.train.batch()
:
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)
...然后使用分别使用image_batch
和label_batch
的{{1}}或image
。
答案 1 :(得分:0)
看起来输入返回3d张量而conv2d需要4d(第一个维度是批量idx) - 如果你只想运行一个图像,首先将它重新整形为[1,180,180,3]。