网上基本上都是tensorflow中给的手写字体的模型的训练过程,没有根据模型识别单个图片的相关内容,废话不多说,接下来给出模型的训练,保存,并根据训练好的模型的识别某个图片的数字。
1.模型的训练
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import time
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()
def weight_variable(shape,namew='w'):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial,name=namew)
def bias_variable(shape,nameb='b'):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial,name=nameb)
def conv2d(x, W,namec='c'):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME',name=namec)
def max_pool_2x2(x,namep='p'):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME',name=namep)
x = tf.placeholder(tf.float32, [None, 784],name='xinput')
y_ = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1])
# Conv1 Layer
W_conv1 = weight_variable([5, 5, 1, 32],'w1')
b_conv1 = bias_variable([32],'b1')
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1,'c1')
h_pool1 = max_pool_2x2(h_conv1,'p1')
# Conv2 Layer
W_conv2 = weight_variable([5, 5, 32, 64],'w2')
b_conv2 = bias_variable([64],'b2')
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],'wf1')
b_fc1 = bias_variable([1024],'bf1')
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,name="prob")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10],'wfull2')
b_fc2 = bias_variable([10],'bf2')
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
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))
tf.global_variables_initializer().run()
saver = tf.train.Saver();
start = time.clock()
for i in range(500):
batch = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
print("step %d, training accuracy %g" % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
print("test accuracy %g" % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
end = time.clock()
print(end - start)
saver.save(sess, "Model/model.ckpt")
关键点:
saver = tf.train.Saver();saver.save(sess, "Model/model.ckpt")要特别注意给变量添加名字 如w2 = tf.placeholder("float", name="w2") b1= tf.Variable(2.0,name="bias")名字是加载模型时主要依据2.加载模型
import tensorflow as tf from skimage import io import numpy as np import cv2 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') sess = tf.Session() saver = tf.train.import_meta_graph("Model/model.ckpt.meta") saver.restore(sess,tf.train.latest_checkpoint('./Model')) im = cv2.imread('1.jpg', cv2.IMREAD_GRAYSCALE).astype(np.float32) # im = cv2.resize(im, (28, 28), interpolation=cv2.INTER_CUBIC) # 图片预处理 # img_gray = cv2.cvtColor(im , cv2.COLOR_BGR2GRAY).astype(np.float32) # 数据从0~255转为-0.5~0.5 img_gray = (im - (255 / 2.0)) / 255 # img_gray = im / 255 x_image = tf.reshape(im, [-1, 28, 28, 1]) # x_img = np.reshape(img_gray, [-1, 784]) W_conv1 = sess.run('w1:0') b_conv1 = sess.run('b1:0') cov1=tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1) p1=max_pool_2x2(cov1) W_conv2 = sess.run('w2:0') b_conv2 = sess.run('b2:0') cov2=tf.nn.relu(conv2d(p1,W_conv2)+b_conv2) p2=max_pool_2x2(cov2) Wf1 = sess.run('wf1:0') bf1 = sess.run('bf1:0') h_pool2_flat = tf.reshape(p2, [-1, 7 * 7 * 64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, Wf1) + bf1) # graph = tf.get_default_graph() # keep_prob = graph.get_tensor_by_name("prob:0") # init = tf.global_variables_initializer() #加载模型绝对不能添加变量初始化 这条语句之后的变量初始化 # sess.run(init) # keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob=1.0) W_fc2 = sess.run('wfull2:0') b_fc2 = sess.run('bf2:0') y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) # print(b_fc2) result=sess.run(y_conv) print(sess.run(y_conv)) print("the result of predict is:",np.argmax(result))
关键点1:模型加载语句注意上面的两个路径一个加了点,一个没有加点saver = tf.train.import_meta_graph("Model/model.ckpt.meta") saver.restore(sess,tf.train.latest_checkpoint('./Model'))
关键点2:获得变量直接加载原模型中的变量Wf1 = sess.run('wf1:0')
关键点3:绝对不能变量初始化,否则模型中的变量会被重新赋值init = tf.global_variables_initializer() #加载模型绝对不能添加变量初始化 这条语句之后的变量重新初始化 sess.run(init)上面的语句不能有
最后附一张结果截图: