阿里天池-零基础入门CV赛事(街景字符识别编码)-Task 3 字符识别模型
1 CNN网络介绍
卷积神经网络(简称CNN)是一类特殊的人工神经网络,是深度学习中重要的一个分支。CNN在很多领域都表现优异,精度和速度比传统计算学习算法高很多。特别是在计算机视觉领域,CNN是解决图像分类、图像检索、物体检测和语义分割的主流模型。
1.1卷积神经网络的层级结构:
数据输入层/ Input layer
卷积计算层/ CONV layer
ReLU激励层 / ReLU layer
池化层 / Pooling layer
全连接层 / FC layer
2 Pytorch代码实现
import os, sys, glob, shutil, json
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
import cv2
from PIL import Image
import numpy as np
from tqdm import tqdm, tqdm_notebook
%pylab inline
import torch
torch.manual_seed(0)
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.benchmark = True
import torchvision.models as models
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
from torch.utils.data.dataset import Dataset
class SVHNDataset(Dataset):
def __init__(self, img_path, img_label, transform=None):
self.img_path = img_path
self.img_label = img_label
if transform is not None:
self.transform = transform
else:
self.transform = None
def __getitem__(self, index):
img = Image.open(self.img_path[index]).convert('RGB')#因为opencv打开的是BGR格式,所以我们需要转换成RGB
if self.transform is not None:
img = self.transform(img)
lbl = np.array(self.img_label[index], dtype=np.int)
lbl = list(lbl) + (5 - len(lbl)) * [10]
return img, torch.from_numpy(np.array(lbl[:5]))
def __len__(self):
return len(self.img_path)
train_path = glob.glob('/mchar_train/*.png')
train_path.sort()
train_json = json.load(open('/mchar_train.json'))
train_label = [train_json[x]['label'] for x in train_json]
print(len(train_path), len(train_label))
train_loader = torch.utils.data.DataLoader(
SVHNDataset(train_path, train_label,
transforms.Compose([
transforms.Resize((64, 128)),
transforms.RandomCrop((60, 120)),
transforms.ColorJitter(0.3, 0.3, 0.2),
transforms.RandomRotation(10),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])),
batch_size=40,
shuffle=True,
num_workers=10,
)
val_path = glob.glob(/mchar_val/*.png')
val_path.sort()
val_json = json.load(open('/mchar_val.json'))
val_label = [val_json[x]['label'] for x in val_json]
print(len(val_path), len(val_label))
val_loader = torch.utils.data.DataLoader(
SVHNDataset(val_path, val_label,
transforms.Compose([
transforms.Resize((60, 120)),
# transforms.ColorJitter(0.3, 0.3, 0.2),
# transforms.RandomRotation(5),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])),
batch_size=40,
shuffle=False,
num_workers=10,
)
#这里使用ResNet18的模型进行特征提取
class SVHN_Model1(nn.Module):
def __init__(self):
super(SVHN_Model1, self).__init__()
model_conv = models.resnet18(pretrained=True)
model_conv.avgpool = nn.AdaptiveAvgPool2d(1)
model_conv = nn.Sequential(*list(model_conv.children())[:-1])
self.cnn = model_conv
self.fc1 = nn.Linear(512, 11)
self.fc2 = nn.Linear(512, 11)
self.fc3 = nn.Linear(512, 11)
self.fc4 = nn.Linear(512, 11)
self.fc5 = nn.Linear(512, 11)
def forward(self, img):
feat = self.cnn(img)
# print(feat.shape)
feat = feat.view(feat.shape[0], -1)
c1 = self.fc1(feat)
c2 = self.fc2(feat)
c3 = self.fc3(feat)
c4 = self.fc4(feat)
c5 = self.fc5(feat)
return c1, c2, c3, c4, c5
def train(train_loader, model, criterion, optimizer, epoch):
# 切换模型为训练模式
model.train()
train_loss = []
for i, (input, target) in enumerate(train_loader):
if use_cuda:
input = input.cuda()
target = target.cuda()
c0, c1, c2, c3, c4 = model(input)
loss = criterion(c0, target[:, 0]) + \
criterion(c1, target[:, 1]) + \
criterion(c2, target[:, 2]) + \
criterion(c3, target[:, 3]) + \
criterion(c4, target[:, 4])
# loss /= 6
#训练神经网络的时候,使用loss.backward()来反向传递修正,修正之后的结果保存在.grad中,因此每轮迭代执行loss.backward()的时候要先对.grad清零
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss.append(loss.item())
return np.mean(train_loss)
def validate(val_loader, model, criterion):
# 切换模型为预测模型
model.eval()
val_loss = []
# 不记录模型梯度信息
with torch.no_grad():
for i, (input, target) in enumerate(val_loader):
if use_cuda:
input = input.cuda()
target = target.cuda()
c0, c1, c2, c3, c4 = model(input)
loss = criterion(c0, target[:, 0]) + \
criterion(c1, target[:, 1]) + \
criterion(c2, target[:, 2]) + \
criterion(c3, target[:, 3]) + \
criterion(c4, target[:, 4])
# loss /= 6
val_loss.append(loss.item())
return np.mean(val_loss)
def predict(test_loader, model, tta=10):
model.eval()
test_pred_tta = None
# TTA 次数
for _ in range(tta):
test_pred = []
with torch.no_grad():
for i, (input, target) in enumerate(test_loader):
if use_cuda:
input = input.cuda()
c0, c1, c2, c3, c4 = model(input)
if use_cuda:
output = np.concatenate([
c0.data.cpu().numpy(),
c1.data.cpu().numpy(),
c2.data.cpu().numpy(),
c3.data.cpu().numpy(),
c4.data.cpu().numpy()], axis=1)
else:
output = np.concatenate([
c0.data.numpy(),
c1.data.numpy(),
c2.data.numpy(),
c3.data.numpy(),
c4.data.numpy()], axis=1)
test_pred.append(output)
test_pred = np.vstack(test_pred)
if test_pred_tta is None:
test_pred_tta = test_pred
else:
test_pred_tta += test_pred
return test_pred_tta
model = SVHN_Model1()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), 0.001)
best_loss = 1000.0
use_cuda = True#使用GPU加速
if use_cuda:
model = model.cuda()
for epoch in range(20):#迭代20次
train_loss = train(train_loader, model, criterion, optimizer, epoch)
val_loss = validate(val_loader, model, criterion)
val_label = [''.join(map(str, x)) for x in val_loader.dataset.img_label]
val_predict_label = predict(val_loader, model, 1)
val_predict_label = np.vstack([
val_predict_label[:, :11].argmax(1),
val_predict_label[:, 11:22].argmax(1),
val_predict_label[:, 22:33].argmax(1),
val_predict_label[:, 33:44].argmax(1),
val_predict_label[:, 44:55].argmax(1),
]).T
val_label_pred = []
for x in val_predict_label:
val_label_pred.append(''.join(map(str, x[x!=10])))
val_char_acc = np.mean(np.array(val_label_pred) == np.array(val_label))
print('Epoch: {0}, Train loss: {1} \t Val loss: {2}'.format(epoch, train_loss, val_loss))
print('Val Acc', val_char_acc)
# 记录下验证集精度
if val_loss < best_loss:
best_loss = val_loss
# print('Find better model in Epoch {0}, saving model.'.format(epoch))
torch.save(model.state_dict(), '/model.pt')