基于tensorflow实现车牌照识别.zip

# -- encoding:utf-8 -- """ 使用TensorFlow训练模型 Create by ibf on 2018/5/28 """ from plate_number.genplate import GenPlate, gen_sample, chars import tensorflow as tf import numpy as np import os import cv2 def make_example(image, label): """ 产生Example对象 :param image: :param label: :return: """ return tf.train.Example(features=tf.train.Features(feature={ 'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image])), 'label': tf.train.Feature(bytes_list=tf.train.BytesList(value=[label])) })) def generate_TFRecord(filename, genplate, height=72, weight=272, num_plat=1000): """ 随机生成num_plat张车牌照并将数据输出形成TFRecord格式 :param filename: TFRecord格式文件存储的路径 :param genplate: 车牌照生成器 :param height: 车牌照高度 :param weight: 车牌照宽度 :param num_plat: 需要生成车牌照的数量 :return: """ writer = tf.python_io.TFRecordWriter(filename) for i in range(num_plat): num, img = gen_sample(genplate, weight, height) # TODO: 因为MxNet中的格式要求导致的问题，必须转换回[height, weight, channels] img = img.transpose(1, 2, 0) img = img.reshape(-1).astype(np.float32) num = np.array(num).reshape(-1).astype(np.int32) ex = make_example(img.tobytes(), num.tobytes()) writer.write(ex.SerializeToString()) writer.close() def read_tfrecord(filename, x_name='image', y_name='label', x_shape=[72, 272, 1], y_shape=[7], batch_size=64, shuffle_data=False, num_threads=1): """ 读取TFRecord文件 :param filename: :param x_name: 给定训练用x的名称 :param y_name: 给定训练用y的名称 :param x_shape: x的格式 :param y_shape: y的格式 :param batch_size: 批大小 :param shuffle_data: 是否混淆数据，如果为True，那么进行shuffle操作 :param num_threads: 线程数目 :return: """ # 获取队列 filename_queue = tf.train.string_input_producer([filename]) # 构建数据读取器 reader = tf.TFRecordReader() # 读取队列中的数据 _, serialized_example = reader.read(filename_queue) # 处理样本 features = tf.parse_single_example( serialized_example, features={ x_name: tf.FixedLenFeature([], tf.string), y_name: tf.FixedLenFeature([], tf.string) } ) # 读取特征 image = tf.decode_raw(features[x_name], tf.float32) label = tf.decode_raw(features[y_name], tf.int32) # 格式重定 image = tf.reshape(image, x_shape) label = tf.reshape(label, y_shape) # 转换为批次的Tensor对象 capacity = batch_size * 6 + 10 if shuffle_data: image, label = tf.train.shuffle_batch([image, label], batch_size=batch_size, capacity=capacity, num_threads=num_threads, min_after_dequeue=int(capacity / 2)) else: image, label = tf.train.batch([image, label], batch_size=batch_size, capacity=capacity, num_threads=num_threads) return image, label def model(images, keep_prob): """ 模型构建 :param images: 图像数据，格式：[batch_size,height,width,channels] :param keep_prob: 进行dropout时候神经元的保留比例 :return: """ with tf.variable_scope('conv1') as scope: weights = tf.get_variable('weights', shape=[3, 3, 3, 32], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) net = tf.nn.conv2d(images, weights, strides=[1, 1, 1, 1], padding='SAME') biases = tf.get_variable('biases', shape=[32], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) net = tf.nn.relu(tf.nn.bias_add(net, biases)) # conv2 with tf.variable_scope('conv2') as scope: weights = tf.get_variable('weights', shape=[3, 3, 32, 32], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) net = tf.nn.conv2d(net, weights, strides=[1, 1, 1, 1], padding='SAME') biases = tf.get_variable('biases', shape=[32], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) net = tf.nn.relu(tf.nn.bias_add(net, biases)) with tf.variable_scope('max_pooling1') as scope: net = tf.nn.max_pool(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') # conv3 with tf.variable_scope('conv3') as scope: weights = tf.get_variable('weights', shape=[3, 3, 32, 64], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) net = tf.nn.conv2d(net, weights, strides=[1, 1, 1, 1], padding='SAME') biases = tf.get_variable('biases', shape=[64], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) net = tf.nn.relu(tf.nn.bias_add(net, biases), name=scope.name) # conv4 with tf.variable_scope('conv4') as scope: weights = tf.get_variable('weights', shape=[3, 3, 64, 64], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) net = tf.nn.conv2d(net, weights, strides=[1, 1, 1, 1], padding='SAME') biases = tf.get_variable('biases', shape=[64], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) net = tf.nn.relu(tf.nn.bias_add(net, biases), name=scope.name) with tf.variable_scope('max_pooling2') as scope: net = tf.nn.max_pool(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', name='pooling2') # conv5 with tf.variable_scope('conv5') as scope: weights = tf.get_variable('weights', shape=[3, 3, 64, 128], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) net = tf.nn.conv2d(net, weights, strides=[1, 1, 1, 1], padding='SAME') biases = tf.get_variable('biases', shape=[128], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) net = tf.nn.relu(tf.nn.bias_add(net, biases), name=scope.name) # conv6 with tf.variable_scope('conv6') as scope: weights = tf.get_variable('weights', shape=[3, 3, 128, 128], dtype=tf.float32, initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32)) net = tf.nn.conv2d(net, weights, strides=[1, 1, 1, 1], padding='VALID') biases = tf.get_variable('biases', shape=[128], dtype=tf.float32, initializer=tf.constant_initializer(0.1)) net = tf.nn.relu(tf.nn.bias_add(net, biases), name=scope.name) # pool3 with tf.variable_scope('max_pool3') as scope: net = tf.nn.max_pool(net, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='VALID', name='pool3') # fc1_flatt