C#cnn神经网络过验证码.rar

# coding:utf-8 from captcha.image import ImageCaptcha import numpy as np import cv2 import tensorflow as tf import random, os, sys import glob from flask import request from flask import Flask import json app = Flask(__name__) class CnnOcr: def __init__(self): self.epoch_max = 10000 # 最大迭代epoch次数 self.batch_size = 8 # 训练时每个批次参与训练的图像数目，显存不足的可以调小 self.lr = 1e-3 # 初始学习率 self.save_epoch = 1 # 每相隔多少个epoch保存一次模型 self.history=0; self.im_width = 128 self.im_height = 64 self.im_total_num = 10000 # 总共生成的验证码图片数量,train目录里面的图片数量 self.train_max_num = self.im_total_num # 训练时读取的最大图片数目 self.val_num = 50 * self.batch_size # 不能大于self.train_max_num 做验证集用 self.words_num = 4 # 每张验证码图片上的数字个数 self.words = "23456789abcdefghijkmnpqrstuvwxyz" #字符范围 self.label_num = self.words_num * len(self.words) self.keep_drop = tf.placeholder(tf.float32) self.x = None self.y = None paths = glob.glob(os.path.join('./dataset/train/', '*.png')) paths.sort() self.paths=paths def captchaOcr(self, img_path): """ 验证码识别 :param img_path: :return: """ im = cv2.imread(img_path) im = cv2.resize(im, (self.im_width, self.im_height)) im = [im] im = np.array(im, dtype=np.float32) im -= 147 output = self.sess.run(self.max_idx_p, feed_dict={self.x: im, self.keep_drop: 1.}) ret = '' for i in output.tolist()[0]: ret = ret + self.words[int(i)] return ret def test(self, img_path): """ 测试接口 :param img_path: :return: """ self.x = tf.placeholder(tf.float32, [None, self.im_height, self.im_width, 3]) # 输入数据 self.pred = self.cnnNet() self.output = tf.nn.sigmoid(self.pred) self.predict = tf.reshape(self.pred, [-1, self.words_num, len(self.words)]) self.max_idx_p = tf.argmax(self.predict, 2) saver = tf.train.Saver() # tfconfig = tf.ConfigProto(allow_soft_placement=True) # tfconfig.gpu_options.per_process_gpu_memory_fraction = 0.3 # 占用显存的比例 # self.ses = tf.Session(config=tfconfig) self.sess = tf.Session() self.sess.run(tf.global_variables_initializer()) # 全局tf变量初始化 # 加载w,b参数 saver.restore(self.sess, tf.train.latest_checkpoint('./model/')) im = cv2.imread(img_path) im = cv2.resize(im, (self.im_width, self.im_height)) im = [im] im = np.array(im, dtype=np.float32) im -= 147 output = self.sess.run(self.max_idx_p, feed_dict={self.x: im, self.keep_drop: 1.}) #ss=self.output.eval(session=self.sess)#转换为numpy数组 #print(ss) ret = '' for i in output.tolist()[0]: ret = ret + self.words[int(i)] print(ret) def train(self): x_train_list, y_train_list, x_val_list, y_val_list = self.getTrainDataset() print('开始转换tensor队列') x_train_list_tensor = tf.convert_to_tensor(x_train_list, dtype=tf.string) y_train_list_tensor = tf.convert_to_tensor(y_train_list, dtype=tf.float32) x_val_list_tensor = tf.convert_to_tensor(x_val_list, dtype=tf.string) y_val_list_tensor = tf.convert_to_tensor(y_val_list, dtype=tf.float32) x_train_queue = tf.train.slice_input_producer(tensor_list=[x_train_list_tensor], shuffle=False) y_train_queue = tf.train.slice_input_producer(tensor_list=[y_train_list_tensor], shuffle=False) x_val_queue = tf.train.slice_input_producer(tensor_list=[x_val_list_tensor], shuffle=False) y_val_queue = tf.train.slice_input_producer(tensor_list=[y_val_list_tensor], shuffle=False) train_im, train_label = self.dataset_opt(x_train_queue, y_train_queue) train_batch = tf.train.batch(tensors=[train_im, train_label], batch_size=self.batch_size, num_threads=2) val_im, val_label = self.dataset_opt(x_val_queue, y_val_queue) val_batch = tf.train.batch(tensors=[val_im, val_label], batch_size=self.batch_size, num_threads=2) print('开启训练') self.learning_rate = tf.placeholder(dtype=tf.float32) # 动态学习率 self.x = tf.placeholder(tf.float32, [None, self.im_height, self.im_width, 3]) # 训练数据 self.y = tf.placeholder(tf.float32, [None, self.label_num]) # 标签 self.pred = self.cnnNet() self.loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=self.pred, labels=self.y)) self.optimizer = tf.train.AdamOptimizer(learning_rate=self.learning_rate).minimize(self.loss) self.predict = tf.reshape(self.pred, [-1, self.words_num, len(self.words)]) self.max_idx_p = tf.argmax(self.predict, 2) self.y_predict = tf.reshape(self.y, [-1, self.words_num, len(self.words)]) self.max_idx_l = tf.argmax(self.y_predict, 2) self.correct_pred = tf.equal(self.max_idx_p, self.max_idx_l) self.accuracy = tf.reduce_mean(tf.cast(self.correct_pred, tf.float32)) tc=0 with tf.Session() as self.sess: # 全局tf变量初始化 self.sess.run(tf.global_variables_initializer()) coordinator = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=self.sess, coord=coordinator) # 模型保存 saver = tf.train.Saver(max_to_keep=3,keep_checkpoint_every_n_hours=3) batch_max = len(x_train_list) // self.batch_size total_step = 1 for epoch_num in range(self.epoch_max): #if tc>=0.8: # lr=lr*0.9 #if tc<0.8: # lr = self.lr * (1 - (epoch_num/self.epoch_max) ** 2) # 动态学习率 lr = self.lr * (1 - (epoch_num/self.epoch_max) ** 2) # 动态学习率 for batch_num in range(batch_max): x_train_tmp, y_train_tmp = self.sess.run(train_batch) # print(x_train_tmp.shape, y_train_tmp.shape) # sys.exit() self.sess.run(self.optimizer, feed_dict={self.x: x_train_tmp, self.y: y_train_tmp, self.learning_rate: lr, self.keep_drop: .5}) # 输出评价标准 if total_step % 50 == 0 or total_step == 1: print() print('epoch:%d/%d batch:%d/%d step:%d lr:%.10f' % ((epoch_num + 1), self.epoch_max, (batch_num + 1), batch_max, total_step, lr)) # 输出训练集评价 train_loss, train_acc = self.sess.run([self.loss, self.accuracy], feed_dict={self.x: x_train_tmp, self.y: y_train_tmp, self.keep_drop: 1.}) print('train_loss:%.10f train_acc:%.10f' % (np.mean(train_loss), train_acc)) # 输出验证集评价 val_loss_list, val_acc_list = [], [] for i in range(int(self.val_num/self.batch_size)): x_val_tmp, y_val_tmp = self.sess.run(val_batch) val_loss, val_acc = self.sess.run([self.loss, self.accuracy], feed_dict={self.x: x_val_tmp, self.y: y_val_tmp, self.keep_drop: 1.}) val_loss_list.append(np.mean(val_loss)) val_acc_list.append(np.mean(val_acc)) print(' val_loss: