参考:https://blog.csdn.net/sparta_117/article/details/66965760
20000遍的训练,结果方面,1和4的图片识别成8,偶尔正确,其他数字只要不变形严重基本正确
训练采用 参考文章的,验证自己修改了一下,下面就是验证代码
import tensorflow as tf
import matplotlib.pyplot as plt
import struct
import numpy as np
model_path =r'D:\MNIST_data\model.ckpt'
test_images_path = r'D:\MNIST_data\t10k-images.idx3-ubyte'
test_labels_path = r'D:\MNIST_data\t10k-labels.idx1-ubyte'
test_images = [] # =mnist.train.images
test_labels = [] # =mnist.train.labels
"""Load MNIST data from `path`"""
with open(test_labels_path, 'rb') as lbpath:
magic, n = struct.unpack('>II', lbpath.read(8))
test_labels = np.fromfile(lbpath, dtype=np.uint8)
with open(test_images_path, 'rb') as imgpath:
magic, num, rows, cols = struct.unpack('>IIII', imgpath.read(16))
test_images = np.fromfile(imgpath, dtype=np.uint8).reshape(len(test_labels), 784)
#图片颜色值255归一化
def imageprepare(im):
# normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
tva = [(255 - x) * 1.0 / 255.0 for x in im] # 0被转成了1.0,颜色被归一化 normalize pixels to 0 and 1. 0
# 把1.0转成0
tvc = []
for x in tva:
if x == 1.0:
tvc.append(0)
else:
tvc.append(x)
return tvc
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
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')
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
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)
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([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)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
init_op = tf.initialize_all_variables()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(init_op)
saver.restore(sess, model_path)#这里使用了之前保存的模型参数
print ("Model restored.")
prediction = tf.argmax(y_conv, 1)
for image in test_images:
predint=prediction.eval(feed_dict={x: [imageprepare(image)],keep_prob: 1.0}, session=sess)
plt.title('recognize result=> ' +str(predint[0]))
plt.imshow(image.reshape([28, 28]))
plt.show()