百度AI Studio深度学习7日入门CV-Day03（CNN车牌识别）
一、课程地址
地址：https://aistudio.baidu.com/aistudio/education/group/info/1149
paddle API：https://paddlepaddle.org.cn/documentation/docs/zh/api_cn/dygraph_cn/Conv2D_cn.html
二、车牌识别
1、获取数据集
数据集地址：https://aistudio.baidu.com/aistudio/datasetdetail/23617
2、代码
2.1 数据读取与转换
import numpy as np
import paddle as paddle
import paddle.fluid as fluid
from PIL import Image
import cv2
import matplotlib.pyplot as plt
import os
from multiprocessing import cpu_count
from paddle.fluid.dygraph import Pool2D,Conv2D
# from paddle.fluid.dygraph import FC
from paddle.fluid.dygraph import Linear
# 生成车牌字符图像列表
data_path = '/home/aistudio/data'
character_folders = os.listdir(data_path)
label = 0
LABEL_temp = {}
if(os.path.exists('./train_data.list')):
os.remove('./train_data.list')
if(os.path.exists('./test_data.list')):
os.remove('./test_data.list')
for character_folder in character_folders:
with open('./train_data.list', 'a') as f_train:
with open('./test_data.list', 'a') as f_test:
if character_folder == '.DS_Store' or character_folder == '.ipynb_checkpoints' or character_folder == 'data23617':
continue
print(character_folder + " " + str(label))
LABEL_temp[str(label)] = character_folder #存储一下标签的对应关系
character_imgs = os.listdir(os.path.join(data_path, character_folder))
for i in range(len(character_imgs)):
if i%10 == 0:
f_test.write(os.path.join(os.path.join(data_path, character_folder), character_imgs[i]) + "\t" + str(label) + '\n')
else:
f_train.write(os.path.join(os.path.join(data_path, character_folder), character_imgs[i]) + "\t" + str(label) + '\n')
label = label + 1
print('图像列表已生成')
2.2 生成训练集和测试集的reader
# 用上一步生成的图像列表定义车牌字符训练集和测试集的reader
def data_mapper(sample):
img, label = sample
img = paddle.dataset.image.load_image(file=img, is_color=False)
img = img.flatten().astype('float32') / 255.0
return img, label
def data_reader(data_list_path):
def reader():
with open(data_list_path, 'r') as f:
lines = f.readlines()
for line in lines:
img, label = line.split('\t')
yield img, int(label)
return paddle.reader.xmap_readers(data_mapper, reader, cpu_count(), 1024)
# 用于训练的数据提供器
train_reader = paddle.batch(reader=paddle.reader.shuffle(reader=data_reader('./train_data.list'), buf_size=512), batch_size=128)
# 用于测试的数据提供器
test_reader = paddle.batch(reader=data_reader('./test_data.list'), batch_size=128)2.3定义网络结构
#定义网络
class MyLeNet(fluid.dygraph.Layer):
def __init__(self):
super(MyLeNet,self).__init__()
self.hidden1_1 = Conv2D(num_channels = 1,#输入图像的通道数
num_filters = 16,#滤波器的个数
filter_size = 5,#滤波器大小
stride=1,act='relu')
self.hidden1_2 = Pool2D(pool_size=2,# 池化核的大小
pool_type='max',#池化类型
pool_stride=1,#池化层的步长
global_pooling=False)
self.hidden2_1 = Conv2D(num_channels = 16,#输入图像的通道数
num_filters = 32,#滤波器的个数
filter_size = 3,#滤波器大小
stride=1,
act='relu')
self.hidden2_2 = Pool2D(pool_size=2,# 池化核的大小
pool_type='max',#池化类型
pool_stride=1,#池化层的步长
global_pooling=False)
self.hidden3_1 = Conv2D(num_channels = 32,#输入图像的通道数
num_filters = 64,#滤波器的个数，和输出特征图个数相同
filter_size = 3,#滤波器大小
stride=1,
act='relu')
self.hidden3_2 = Pool2D(pool_size=3,# 池化核的大小
pool_type='max',#池化类型
pool_stride=1,#池化层的步长
global_pooling=False)
self.hidden4 = Linear(input_dim = 64*8*8,
output_dim = 65,
act = 'softmax')
def forward(self,input):
x1 = self.hidden1_1(input)
x2 = self.hidden1_2(x1)
x3 = self.hidden2_1(x2)
x4 = self.hidden2_2(x3)
x5 = self.hidden3_1(x4)
x6 = self.hidden3_2(x5)
x7 = fluid.layers.reshape(x6,shape=[-1,64*8*8])
y = self.hidden4(x7)
return y2.4 训练
with fluid.dygraph.guard():
model=MyLeNet() #模型实例化
model.train() #训练模式
opt=fluid.optimizer.SGDOptimizer(learning_rate=0.001, parameter_list=model.parameters())#优化器选用SGD随机梯度下降，学习率为0.001.
epochs_num = 200#迭代次数为2
for pass_num in range(epochs_num):
for batch_id,data in enumerate(train_reader()):
images=np.array([x[0].reshape(1,20,20) for x in data],np.float32)
labels = np.array([x[1] for x in data]).astype('int64')
labels = labels[:, np.newaxis]
image=fluid.dygraph.to_variable(images)
# print(image.shape)#[128, 1, 20, 20]
label=fluid.dygraph.to_variable(labels)
predict=model(image)#预测
loss=fluid.layers.cross_entropy(predict,label)
avg_loss=fluid.layers.mean(loss)#获取loss值
acc=fluid.layers.accuracy(predict,label)#计算精度
if batch_id!=0 and batch_id%50==0:
print("train_pass:{},batch_id:{},train_loss:{},train_acc:{}".format(pass_num,batch_id,avg_loss.numpy(),acc.numpy()))
avg_loss.backward()
opt.minimize(avg_loss)
model.clear_gradients()
fluid.save_dygraph(model.state_dict(),'MyLeNet')#保存模型2.5 测试集验证
在这里插入代码片
#模型校验
with fluid.dygraph.guard():
accs = []
model=MyLeNet()#模型实例化
model_dict,_=fluid.load_dygraph('MyLeNet')
model.load_dict(model_dict)#加载模型参数
model.eval()#评估模式
for batch_id,data in enumerate(test_reader()):#测试集
images=np.array([x[0].reshape(1,20,20) for x in data],np.float32)
labels = np.array([x[1] for x in data]).astype('int64')
labels = labels[:, np.newaxis]
image=fluid.dygraph.to_variable(images)
label=fluid.dygraph.to_variable(labels)
predict=model(image)#预测
acc=fluid.layers.accuracy(predict,label)
accs.append(acc.numpy()[0])
avg_acc = np.mean(accs)
print(avg_acc)2.5 预测
在这里插入代码片
# 对车牌图片进行处理，分割出车牌中的每一个字符并保存
license_plate = cv2.imread('./车牌.png')
gray_plate = cv2.cvtColor(license_plate, cv2.COLOR_RGB2GRAY)
ret, binary_plate = cv2.threshold(gray_plate, 175, 255, cv2.THRESH_BINARY)
result = []
for col in range(binary_plate.shape[1]):
result.append(0)
for row in range(binary_plate.shape[0]):
result[col] = result[col] + binary_plate[row][col]/255
character_dict = {}
num = 0
i = 0
while i < len(result):
if result[i] == 0:
i += 1
else:
index = i + 1
while result[index] != 0:
index += 1
character_dict[num] = [i, index-1]
num += 1
i = index
for i in range(8):
if i==2:
continue
padding = (170 - (character_dict[i][1] - character_dict[i][0])) / 2
ndarray = np.pad(binary_plate[:,character_dict[i][0]:character_dict[i][1]], ((0,0), (int(padding), int(padding))), 'constant', constant_values=(0,0))
ndarray = cv2.resize(ndarray, (20,20))
cv2.imwrite('./' + str(i) + '.png', ndarray)
def load_image(path):
img = paddle.dataset.image.load_image(file=path, is_color=False)
img = img.astype('float32')
img = img[np.newaxis, ] / 255.0
return img
#将标签进行转换
print('Label:',LABEL_temp)
match = {'A':'A','B':'B','C':'C','D':'D','E':'E','F':'F','G':'G','H':'H','I':'I','J':'J','K':'K','L':'L','M':'M','N':'N',
'O':'O','P':'P','Q':'Q','R':'R','S':'S','T':'T','U':'U','V':'V','W':'W','X':'X','Y':'Y','Z':'Z',
'yun':'云','cuan':'川','hei':'黑','zhe':'浙','ning':'宁','jin':'津','gan':'赣','hu':'沪','liao':'辽','jl':'吉','qing':'青','zang':'藏',
'e1':'鄂','meng':'蒙','gan1':'甘','qiong':'琼','shan':'陕','min':'闽','su':'苏','xin':'新','wan':'皖','jing':'京','xiang':'湘','gui':'贵',
'yu1':'渝','yu':'豫','ji':'冀','yue':'粤','gui1':'桂','sx':'晋','lu':'鲁',
'0':'0','1':'1','2':'2','3':'3','4':'4','5':'5','6':'6','7':'7','8':'8','9':'9'}
L = 0
LABEL ={}
for V in LABEL_temp.values():
LABEL[str(L)] = match[V]
L += 1
print(LABEL)
#构建预测动态图过程
with fluid.dygraph.guard():
model=MyLeNet()#模型实例化
model_dict,_=fluid.load_dygraph('MyLeNet')
model.load_dict(model_dict)#加载模型参数
model.eval()#评估模式
lab=[]
for i in range(8):
if i==2:
continue
infer_imgs = []
infer_imgs.append(load_image('./' + str(i) + '.png'))
infer_imgs = np.array(infer_imgs)
infer_imgs = fluid.dygraph.to_variable(infer_imgs)
result=model(infer_imgs)
lab.append(np.argmax(result.numpy()))
# print(lab)
display(Image.open('./车牌.png'))
print('\n车牌识别结果为：',end='')
for i in range(len(lab)):
print(LABEL[str(lab[i])],end='')
2.6结果
训练过程
测试集精度
预测结果
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
