我正在尝试使用Tensorflow进行2级图像分类。 虽然它能够在RGB版本中成功执行，但我尝试在灰度级中执行此操作以提高计算速度。更改频道数后，我收到错误消息。
ValueError: Can not feed value of shape (10, 3072) for Tensor 'Placeholder: 0', which has shape '(?, 1024)'
当RGB显示在下面时操作的代码
import sys
sys.path.append('/usr/local/opt/opencv3/lib/python3.5.4/site-packages')
import cv2
import numpy as np
import tensorflow as tf
import tensorflow.python.platform
import os
log_dir = '/tmp/tensorflow/mnist/logs/simple01'
if tf.gfile.Exists(log_dir):
tf.gfile.DeleteRecursively(log_dir)
tf.gfile.MakeDirs(log_dir)
NUM_CLASSES = 2
IMAGE_SIZE = 32
IMAGE_PIXELS = IMAGE_SIZE*IMAGE_SIZE*3
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_string('train', 'train2.txt', 'File name of train data')
flags.DEFINE_string('test', 'test2.txt', 'File name of train data')
flags.DEFINE_string('image_dir', 'data2', 'Directory of images')
flags.DEFINE_string('train_dir', '/tmp/data', 'Directory to put the training data.')
flags.DEFINE_integer('max_steps', 200, 'Number of steps to run trainer.')
flags.DEFINE_integer('batch_size', 10, 'Batch size'
'Must divide evenly into the dataset sizes.')
flags.DEFINE_float('learning_rate', 1e-5, 'Initial learning rate.')
def inference(images_placeholder, keep_prob):
"""
images_placeholder:imaging placeholder
keep_prob: dropout rate place_holder
y_conv:
"""
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_image = tf.reshape(images_placeholder, [-1, 32, 32, 3])
with tf.name_scope('conv1') as scope:
W_conv1 = weight_variable([5, 5, 3, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu6(conv2d(x_image, W_conv1) + b_conv1)
tf.summary.histogram("wc1", W_conv1)
with tf.name_scope('pool1') as scope:
h_pool1 = max_pool_2x2(h_conv1)
with tf.name_scope('conv2') as scope:
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu6(conv2d(h_pool1, W_conv2) + b_conv2)
tf.summary.histogram("wc2", W_conv2)
with tf.name_scope('pool2') as scope:
h_pool2 = max_pool_2x2(h_conv2)
with tf.name_scope('fc1') as scope:
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.relu6(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
with tf.name_scope('fc2') as scope:
W_fc2 = weight_variable([1024, NUM_CLASSES])
b_fc2 = bias_variable([NUM_CLASSES])
with tf.name_scope('softmax') as scope:
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
return y_conv
def loss(logits, labels):
"""
logits: tensor, float - [batch_size, NUM_CLASSES]
labels: tensor, int32 - [batch_size, NUM_CLASSES]
cross_entropy: tensor, float
"""
cross_entropy = -tf.reduce_sum(labels*tf.log(logits))
tf.summary.scalar("cross_entropy", cross_entropy)
return cross_entropy
def training(loss, learning_rate):
"""
loss: tensor, loss()
learning_rate:
train_step:
"""
train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss)
return train_step
def accuracy(logits, labels):
"""(accuracy)
logits: inference()
labels: tensor, int32 - [batch_size, NUM_CLASSES]
accuracy: (float)
"""
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
tf.summary.scalar("accuracy", accuracy)
return accuracy
if __name__ == '__main__':
f = open(FLAGS.train, 'r')
train_image = []
train_label = []
for line in f:
line = line.rstrip()
l = line.split()
img = cv2.imread(FLAGS.image_dir + '/' + l[0])
img = cv2.resize(img, (32, 32))
train_image.append(img.flatten().astype(np.float32)/255.0)
tmp = np.zeros(NUM_CLASSES)
tmp[int(l[1])] = 1
train_label.append(tmp)
train_image = np.asarray(train_image)
train_label = np.asarray(train_label)
f.close()
f = open(FLAGS.test, 'r')
test_image = []
test_label = []
for line in f:
line = line.rstrip()
l = line.split()
img = cv2.imread(FLAGS.image_dir + '/' + l[0])
img = cv2.resize(img, (32, 32))
test_image.append(img.flatten().astype(np.float32)/255.0)
tmp = np.zeros(NUM_CLASSES)
tmp[int(l[1])] = 1
test_label.append(tmp)
test_image = np.asarray(test_image)
test_label = np.asarray(test_label)
f.close()
with tf.Graph().as_default():
images_placeholder = tf.placeholder("float", shape=(None, IMAGE_PIXELS))
labels_placeholder = tf.placeholder("float", shape=(None, NUM_CLASSES))
keep_prob = tf.placeholder("float")
logits = inference(images_placeholder, keep_prob)
loss_value = loss(logits, labels_placeholder)
train_op = training(loss_value, FLAGS.learning_rate)
acc = accuracy(logits, labels_placeholder)
saver = tf.train.Saver()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(FLAGS.train_dir, sess.graph)
for step in range(FLAGS.max_steps):
for i in range(int(len(train_image)/FLAGS.batch_size)):
batch = FLAGS.batch_size*i
sess.run(train_op, feed_dict={
images_placeholder: train_image[batch:batch+FLAGS.batch_size],
labels_placeholder: train_label[batch:batch+FLAGS.batch_size],
keep_prob: 0.5})
train_accuracy = sess.run(acc, feed_dict={
images_placeholder: train_image,
labels_placeholder: train_label,
keep_prob: 1.0})
print("step %d, training accuracy %g"%(step, train_accuracy))
summary_str = sess.run(summary_op, feed_dict={
images_placeholder: train_image,
labels_placeholder: train_label,
keep_prob: 1.0})
summary_writer.add_summary(summary_str, step)
print("test accuracy %g"%sess.run(acc, feed_dict={
images_placeholder: test_image,
labels_placeholder: test_label,
keep_prob: 1.0}))
save_path = saver.save(sess, os.getcwd() + "\\model.ckpt")
我更改了第20行以使用Grayscale
IMAGE_PIXELS = IMAGE_SIZE*IMAGE_SIZE*1
并将第62行更改为70
x_image = tf.reshape(images_placeholder, [-1, 32, 32, 1])
with tf.name_scope('conv1') as scope:
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
tf.summary.histogram("wc1", W_conv1)
我收到了一个错误。 使用的图像也转换为灰色信息，但似乎RGB仍然是（10,3072）和1024×3的形式。
请告诉我是否有解决方案。请。
答案 0 :(得分：1)
您的问题来自这样一个事实：即使您更新了Tensorflow占位符，每个像素只有一个频道，您仍然会使用RGB中的OpenCV加载图像并尝试将它们直接送到网络。
在使用cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)之前，您应该使用flatten将它们转换为灰度。