【深度学习】用PaddlePaddle进行车牌识别（二）

　　上节我们讲了第一部分，如何用生成简易的车牌，这节课中我们会用PaddlePaddle来识别生成的车牌。

---

数据读取

　　在上一节生成车牌时，我们可以分别生成训练数据和测试数据，方法如下（完整代码在这里）：

 # 将生成的车牌图片写入文件夹，对应的label写入label.txt
 def genBatch(self, batchSize,pos,charRange, outputPath,size):
     if (not os.path.exists(outputPath)):
         os.mkdir(outputPath)
     outfile = open('label.txt','w')
     for i in xrange(batchSize):
             plateStr,plate = G.genPlateString(-1,-1)
             print plateStr,plate
             img =  G.generate(plateStr);
             img = cv2.resize(img,size);
             cv2.imwrite(outputPath + "/" + str(i).zfill(2) + ".jpg", img);
             outfile.write(str(plate)+"\n")        

　　生成好数据后，我们写一个reader来读取数据 ( reador.py )

 def reader_creator(data,label):
     def reader():
         for i in xrange(len(data)):
             yield data[i,:],int(label[i])
     return reader

　　灌入模型时，我们需要调用paddle.batch函数，将数据shuffle后批量灌入模型中：

 # 读取训练数据
 train_reader = paddle.batch(paddle.reader.shuffle(
                 reador.reader_creator(X_train,Y_train),buf_size=200),
                 batch_size=16)

 # 读取验证数据
  val_reader = paddle.batch(paddle.reader.shuffle(
                 reador.reader_creator(X_val,Y_val),buf_size=200),
                 batch_size=16)
        trainer.train(reader=train_reader,num_passes=20,event_handler=event_handler)

---

构建网络模型

　　因为我们训练的是端到端的车牌识别，所以一开始构建了两个卷积-池化层训练，训练完后同步训练7个全连接层，分别对应车牌的7位字符，最后将其拼接起来，与原始的label计算Softmax值，预测训练结果。　

 def get_network_cnn(self):
    # 加载data和label
     x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(self.data))
     y = paddle.layer.data(name='y', type=paddle.data_type.integer_value(self.label))
     # 构建卷积-池化层-1
     conv_pool_1 = paddle.networks.simple_img_conv_pool(
             input=x,
             filter_size=12,
             num_filters=50,
             num_channel=1,
             pool_size=2,
             pool_stride=2,
             act=paddle.activation.Relu())
     drop_1 = paddle.layer.dropout(input=conv_pool_1, dropout_rate=0.5)
     # 构建卷积-池化层-2
     conv_pool_2 = paddle.networks.simple_img_conv_pool(
             input=drop_1,
             filter_size=5,
             num_filters=50,
             num_channel=20,
             pool_size=2,
             pool_stride=2,
             act=paddle.activation.Relu())
     drop_2 = paddle.layer.dropout(input=conv_pool_2, dropout_rate=0.5)

     # 全连接层
     fc = paddle.layer.fc(input = drop_2, size = 120)
     fc1_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
     fc1 = paddle.layer.fc(input = fc1_drop,size = 65,act = paddle.activation.Linear())

     fc2_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
     fc2 = paddle.layer.fc(input = fc2_drop,size = 65,act = paddle.activation.Linear())

     fc3_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
     fc3 = paddle.layer.fc(input = fc3_drop,size = 65,act = paddle.activation.Linear())

     fc4_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
     fc4 = paddle.layer.fc(input = fc4_drop,size = 65,act = paddle.activation.Linear())

     fc5_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
     fc5 = paddle.layer.fc(input = fc5_drop,size = 65,act = paddle.activation.Linear())

     fc6_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
     fc6 = paddle.layer.fc(input = fc6_drop,size = 65,act = paddle.activation.Linear())

     fc7_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
     fc7 = paddle.layer.fc(input = fc7_drop,size = 65,act = paddle.activation.Linear())

     # 将训练好的7个字符的全连接层拼接起来
     fc_concat = paddle.layer.concact(input = [fc21, fc22, fc23, fc24,fc25,fc26,fc27], axis = 0)
     predict = paddle.layer.classification_cost(input = fc_concat,label = y,act=paddle.activation.Softmax())
     return predict

---

训练模型

　　　构建好网络模型后，就是比较常见的步骤了，譬如初始化，定义优化方法， 定义训练参数，定义训练器等等，再把第一步里我们写好的数据读取的方式放进去，就可以正常跑模型了。

 class NeuralNetwork(object):
     def __init__(self,X_train,Y_train,X_val,Y_val):
         paddle.init(use_gpu = with_gpu,trainer_count=1)

         self.X_train = X_train
         self.Y_train = Y_train
         self.X_val = X_val
         self.Y_val = Y_val

     def get_network_cnn(self):

         x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(self.data))
         y = paddle.layer.data(name='y', type=paddle.data_type.integer_value(self.label))
         conv_pool_1 = paddle.networks.simple_img_conv_pool(
             input=x,
             filter_size=12,
             num_filters=50,
             num_channel=1,
             pool_size=2,
             pool_stride=2,
             act=paddle.activation.Relu())
         drop_1 = paddle.layer.dropout(input=conv_pool_1, dropout_rate=0.5)
         conv_pool_2 = paddle.networks.simple_img_conv_pool(
             input=drop_1,
             filter_size=5,
             num_filters=50,
             num_channel=20,
             pool_size=2,
             pool_stride=2,
             act=paddle.activation.Relu())
         drop_2 = paddle.layer.dropout(input=conv_pool_2, dropout_rate=0.5)

         fc = paddle.layer.fc(input = drop_2, size = 120)
         fc1_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
         fc1 = paddle.layer.fc(input = fc1_drop,size = 65,act = paddle.activation.Linear())

         fc2_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
         fc2 = paddle.layer.fc(input = fc2_drop,size = 65,act = paddle.activation.Linear())

         fc3_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
         fc3 = paddle.layer.fc(input = fc3_drop,size = 65,act = paddle.activation.Linear())

         fc4_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
         fc4 = paddle.layer.fc(input = fc4_drop,size = 65,act = paddle.activation.Linear())

         fc5_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
         fc5 = paddle.layer.fc(input = fc5_drop,size = 65,act = paddle.activation.Linear())

         fc6_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
         fc6 = paddle.layer.fc(input = fc6_drop,size = 65,act = paddle.activation.Linear())

         fc7_drop = paddle.layer.dropout(input = fc,dropout_rate = 0.5)
         fc7 = paddle.layer.fc(input = fc7_drop,size = 65,act = paddle.activation.Linear())

         fc_concat = paddle.layer.concact(input = [fc21, fc22, fc23, fc24,fc25,fc26,fc27], axis = 0)
         predict = paddle.layer.classification_cost(input = fc_concat,label = y,act=paddle.activation.Softmax())
         return predict

     # 定义训练器
     def get_trainer(self):

         cost = self.get_network()

         #获取参数
         parameters = paddle.parameters.create(cost)

         optimizer = paddle.optimizer.Momentum(
                                 momentum=0.9,
                                 regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
                                 learning_rate=0.001,
                                 learning_rate_schedule = "pass_manual")

         # 创建训练器
         trainer = paddle.trainer.SGD(
                 cost=cost, parameters=parameters, update_equation=optimizer)
         return trainer

     # 开始训练
     def start_trainer(self,X_train,Y_train,X_val,Y_val):
         trainer = self.get_trainer()

         result_lists = []
         def event_handler(event):
             if isinstance(event, paddle.event.EndIteration):
                 if event.batch_id % 10 == 0:
                     print "\nPass %d, Batch %d, Cost %f, %s" % (
                         event.pass_id, event.batch_id, event.cost, event.metrics)
             if isinstance(event, paddle.event.EndPass):
                     # 保存训练好的参数
                 with open('params_pass_%d.tar' % event.pass_id, 'w') as f:
                     parameters.to_tar(f)
                 # feeding = ['x','y']
                 result = trainer.test(
                         reader=val_reader)
                             # feeding=feeding)
                 print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)

                 result_lists.append((event.pass_id, result.cost,
                         result.metrics['classification_error_evaluator']))

         # 开始训练
         train_reader = paddle.batch(paddle.reader.shuffle(
                 reador.reader_creator(X_train,Y_train),buf_size=200),
                 batch_size=16)

         val_reader = paddle.batch(paddle.reader.shuffle(
                 reador.reader_creator(X_val,Y_val),buf_size=200),
                 batch_size=16)
         # val_reader = paddle.reader(reador.reader_creator(X_val,Y_val),batch_size=16)

         trainer.train(reader=train_reader,num_passes=20,event_handler=event_handler)

---

输出结果

　　上一步训练完以后，保存训练完的模型，然后写一个test.py进行预测，需要注意的是，在预测时，构建的网络结构得和训练的网络结构相同。

#批量预测测试图片准确率
python test.py /Users/shelter/test

##输出结果示例
output:
预测车牌号码为:津 K 4 2 R M Y
输入图片数量:100
输入图片行准确率:0.72
输入图片列准确率:0.86

　　如果是一次性只预测一张的话，在终端里会显示原始的图片与预测的值，如果是批量预测的话，会打印出预测的总准确率，包括行与列的准确率。

---

总结

　　　车牌识别的方法有很多，商业化落地的方法也很成熟，传统的方法需要对图片灰度化，字符进行切分等，需要很多数据预处理的过程，端到端的方法可以直接将原始的图片灌进去进行训练，最后出来预测的车牌字符的结果，这个方法在构建了两层卷积-池化网络结构后，并行训练了7个全连接层来进行车牌的字符识别，可以实现端到端的识别。但是在实际训练过程中，仍然有一些问题，譬如前几个训练的全连接层的准确率要比最后一两个的准确率高，大家可以分别打印出每一个全连接层的训练结果准确率对比一下，可能是由于训练还没有收敛导致的，也可能有其他原因，如果在做的过程中发现有什么问题，或者有更好的方法，欢迎留言~

参考文献：

1.我的github：https://github.com/huxiaoman7/mxnet-cnn-plate-recognition