import os
import tensorflow as tf
from PIL import Image
import matplotlib.pyplot as plt
import readfileTFRecord
import input_data_record
def weight_varible(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')
#mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
print("Loading Done!")
sess = tf.InteractiveSession()
paras
W_conv1 = weight_varible([5, 5, 1, 32])
b_conv1 = bias_variable([32])
conv layer-1
x = tf.placeholder(tf.float32, [None, 784])
x_image = tf.reshape(x, [-1, 28, 28, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
conv layer-2
W_conv2 = weight_varible([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)
full connection
W_fc1 = weight_varible([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
dropout
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
output layer: softmax
W_fc2 = weight_varible([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
y_ = tf.placeholder(tf.float32, [None, 10])
model training
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.arg_max(y_conv, 1), tf.arg_max(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sess.run(tf.initialize_all_variables())
img, label = readfileTFRecord.read_and_decode("train_min.tfrecords")
img_batch, label_batch = tf.train.shuffle_batch([img, label],
batch_size=3, capacity=30,
min_after_dequeue=9)
#img_batch,label_batch = input_data_record.get_batch(img,label,28,28,3,30)
init = tf.initialize_all_variables()
#with tf.Session() as sess:
sess.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess,coord=coord)
try:
for i in range(30):
if coord.should_stop():
break
val, l= sess.run([img_batch, label_batch])
#l = to_categorical(l, 12)
train_accuacy = accuracy.eval(feed_dict={x: val, y_: l, keep_prob: 1.0})
print("step %d, training accuracy %g"%(i, train_accuacy))
sess.graph.finalize()
train_step.run(feed_dict = {x: val, y_: l, keep_prob: 1.0})
print(val.shape, l)
except tf.errors.OutOfRangeError:
print('Done training --epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
sess.close()
报错:
ValueError: Cannot feed value of shape (3, 28, 28, 1) for Tensor u'Placeholder:0', which has shape '(?, 784)'