criterion = nn.CrossEntropyLoss(reduction='sum')
optimizer = torch.optim.Adam(model.parameters(), lr=lr)
best_epoch, best_loss, best_acc = -1, 1000.0, 0
# 模型训练，并保存最优参数
for epoch in range(epochs):
train_loss = model.mytraining(train_loader, criterion, optimizer,
device)
val_loss = model.myvalidating(val_loader, criterion, device)
# 记录下验证集精度
if val_loss < best_loss:
best_epoch, best_loss = epoch, val_loss
# 保存model可学习参数
torch.save(model.state_dict(), 'Model/model.pt')
# 打印相关信息
Tools.printInfo(epoch, train_loss, val_loss, best_epoch, best_loss)
else:
# 预测过程
test_path, test_label = Tools.dataFromPath(test_img_path)
test_dataset = SVHNDataset(
test_path, test_label,
transforms.Compose([
transforms.Resize((64, 128)),
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])
]))
test_loader = torch.utils.data.DataLoader(
test_dataset,
