运行出现以下情况，
using cpu device.
Traceback (most recent call last):
File “E:\桌面\pytorch项目练习\predict.py”, line 64, in
main()
File “E:\桌面\pytorch项目练习\predict.py”, line 45, in main
model.load_state_dict(torch.load(weights_path))
File “C:\Users\Administrator\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py”, line 1497, in load_state_dict
raise RuntimeError(‘Error(s) in loading state_dict for {}:\n\t{}’.format(
RuntimeError: Error(s) in loading state_dict for AlexNet/VGG16:
size mismatch for classifier.6.weight: copying a param with shape torch.Size([2, 2048]) from checkpoint, the shape in current model is torch.Size([3, 2048]).
size mismatch for classifier.6.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([3]).
我们在train.py文件里num_classes值没有改成我们对应需要训练类数；或者是predict.py里num_classes值改成我们这次预测类数
解决办法：修改值重新训练，重新运行
net = AlexNet(num_classes=2, init_weights=True)
model = AlexNet(num_classes=2).to(device)
using cpu device.
Traceback (most recent call last):
File "E:\桌面\pytorch项目练习\carb实战\Test2_alexnet\predict.py", line 64, in <module>
main()
File "E:\桌面\pytorch项目练习\carb实战\Test2_alexnet\predict.py", line 45, in main
model.load_state_dict(torch.load(weights_path))
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py", line 1497, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {
}:\n\t{
}'.format(
RuntimeError: Error(s) in loading state_dict for AlexNet:
size mismatch for classifier.6.weight: copying a param with shape torch.Size([2, 2048]) from checkpoint, the shape in current model is torch.Size([3, 2048]).
size mismatch for classifier.6.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([3]).