【验证码识别项目demo】4--生成训练batch，定义和训练卷积神经网络

# 生成一个训练batch
def get_next_batch(batch_size=128):
    batch_x = np.zeros([batch_size, IMAGE_HEIGHT * IMAGE_WIDTH])#128,60*160
    batch_y = np.zeros([batch_size, MAX_CAPTCHA * CHAR_SET_LEN])#128,4*63
    # 有时生成图像大小不是(60, 160, 3)
    def wrap_gen_captcha_text_and_image():
        while True:
            text, image = gen_captcha_text_and_image_new()
            if image.shape == (60, 160, 3):
                return text, image

    for i in range(batch_size):
        text, image = wrap_gen_captcha_text_and_image()
        image = convert2gray(image)
        #把image展成一维，然后除以255 eg:[0.94901961 0.96470588 0.96470588...]
        batch_x[i, :] = image.flatten() / 255  # (image.flatten()-128)/128  mean为0
        batch_y[i, :] = text2vec(text)
    return batch_x, batch_y
####################################################################
X = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT * IMAGE_WIDTH])
Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHA * CHAR_SET_LEN])
keep_prob = tf.placeholder(tf.float32)  # dropout

# 定义CNN
def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):
    x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
    # 3 conv layer
    w_c1 = tf.Variable(w_alpha * tf.random_normal([3, 3, 1, 32]))
    b_c1 = tf.Variable(b_alpha * tf.random_normal([32]))
    conv1 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x, w_c1, strides=[1, 1, 1, 1], padding='SAME'), b_c1))
    conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    conv1 = tf.nn.dropout(conv1, keep_prob)

    w_c2 = tf.Variable(w_alpha * tf.random_normal([3, 3, 32, 64]))
    b_c2 = tf.Variable(b_alpha * tf.random_normal([64]))
    conv2 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv1, w_c2, strides=[1, 1, 1, 1], padding='SAME'), b_c2))
    conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    conv2 = tf.nn.dropout(conv2, keep_prob)

    w_c3 = tf.Variable(w_alpha * tf.random_normal([3, 3, 64, 64]))
    b_c3 = tf.Variable(b_alpha * tf.random_normal([64]))
    conv3 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv2, w_c3, strides=[1, 1, 1, 1], padding='SAME'), b_c3))
    conv3 = tf.nn.max_pool(conv3, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    conv3 = tf.nn.dropout(conv3, keep_prob)
    #60*160*1->30*80*32->15*40*64->8*20*64
    # Fully connected layer
    w_d = tf.Variable(w_alpha * tf.random_normal([8 * 20 * 64, 1024]))
    b_d = tf.Variable(b_alpha * tf.random_normal([1024]))
    #dense = tf.reshape(conv3, [-1, w_d.get_shape().as_list()[0]])
    #上面一行代码意思与下一行代码一样,10240=8*20*64
    dense = tf.reshape(conv3, [-1, 10240])
    dense = tf.nn.relu(tf.add(tf.matmul(dense, w_d), b_d))
    dense = tf.nn.dropout(dense, keep_prob)

    w_out = tf.Variable(w_alpha * tf.random_normal([1024, MAX_CAPTCHA * CHAR_SET_LEN]))
    b_out = tf.Variable(b_alpha * tf.random_normal([MAX_CAPTCHA * CHAR_SET_LEN]))
    out = tf.add(tf.matmul(dense, w_out), b_out)
    # out = tf.nn.softmax(out)
    return out

# 训练
def train_crack_captcha_cnn():
    output = crack_captcha_cnn()
    # loss
    # loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output, Y))
    loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
    # 最后一层用来分类的softmax和sigmoid有什么不同？
    # optimizer 为了加快训练 learning_rate应该开始大，然后慢慢衰
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)

    predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN])
    max_idx_p = tf.argmax(predict, 2)
    max_idx_l = tf.argmax(tf.reshape(Y, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
    correct_pred = tf.equal(max_idx_p, max_idx_l)
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

    saver = tf.train.Saver()
    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        step = 0
        while True:
            batch_x, batch_y = get_next_batch(64)
            _, loss_ = sess.run([optimizer, loss], feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.75})
            #print("No. %d steps,the loss is %f " %(step, loss_))

            # 每100 step计算一次准确率
            if step % 100 == 0:
                batch_x_test, batch_y_test = get_next_batch(100)
                acc = sess.run(accuracy, feed_dict={X: batch_x_test, Y: batch_y_test, keep_prob: 1.})
                print("No. %d steps,the acc is %f " %(step, acc))
                # 如果准确率大于50%,保存模型,完成训练
                if acc > 0.99:
                    saver.save(sess, "./tmp/ckpt/model", global_step=step)
                    break

            step += 1

 

然后我们调用train_crack_captcha_cnn()函数进行训练

train_crack_captcha_cnn()

大概进行到8000步左右，训练正确率到达99%以上，停止训练，进行测试