Eric Shaw
> 我认为你说的是对的，focalloss的alpha是用来平衡正负样本的损失的，不是用来平衡类样本数量的。这是我的理解。
> This is a great work. However, when I try to reproduce results on the ImageNet dataset, there is a 1% accuracy gap between mine and that in your paper....
> > > This is a great work. However, when I try to reproduce results on the ImageNet dataset, there is a 1% accuracy gap between mine and that in...
``` class TestImageDataset(Dataset): def __init__(self, root, transform, classes2label=None): super(TestImageDataset, self).__init__() self.root = root self.transform = transform self.classes2label = classes2label self.image_file_list, self.label_list = self.parse_txt() def __len__(self): return len(self.image_file_list) def __getitem__(self, idx):...
> > ``` > > class TestImageDataset(Dataset): > > def __init__(self, root, transform, classes2label=None): > > super(TestImageDataset, self).__init__() > > self.root = root > > self.transform = transform > >...
so sorry, im not familiar with pull request, but why my new commit failed
是最新版，（deepin15.5）
> By the way, It works ok when I using your demo.py to inference. i am in trouble with demo.py, because the default ckpt vgg16_reducedfc.pth from the Internet has missing...
@chxy95 So sorry, i solved the problem without closing the issue. As for this problem, i have got some solutions. 1. First, check out pytorch version, perhaps a newer version...