pytorch 知识点总结(持续更新)

1、argparse的使用 （Python脚本时传入参数的三种方式之一：https://blog.csdn.net/u012426298/article/details/80263507）

import argparse#必备
parser = argparse.ArgumentParser(description='PyTorch ImageNet Training')#必备
parser.add_argument('data', metavar='DIR',
                    help='path to dataset')#
parser.add_argument('-a', '--arch', metavar='ARCH', default='resnet18',
                    choices=model_names,
                    help='model architecture: ' +
                        ' | '.join(model_names) +
                        ' (default: resnet18)')
parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
                    help='number of data loading workers (default: 4)')
parser.add_argument('--epochs', default=90, type=int, metavar='N',
                    help='number of total epochs to run')

parser.add_argument('--lr', '--learning-rate', default=0.1, type=float,
                    metavar='LR', help='initial learning rate')


args = parser.parse_args()#必备

traindir = os.path.join(args.data, 'train')
    valdir = os.path.join(args.data, 'val')###
optimizer = torch.optim.SGD(model.parameters(), args.lr,#
                                momentum=args.momentum,
                                weight_decay=args.weight_decay)

执行文件：

python main.py -a alexnet --lr 0.01 [imagenet-folder with train and val folders]

2、限制使用哪个GPU

os.environ["CUDA_VISIBLE_DEVICES"] = "1"

3、读出Tensor里面的值

4、在分类任务中找出单个类别的准确率（每一个类别）

class_correct = list(0. for i in range(10))#10是类别的个数
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()#每一个batch的(predicted==labels)
        for i in range(4):#4是每一个batch的个数
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1


for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))#每一个类别的准确率

5、