validate loss cannot update

[Arui1]

loss and prec1 during training is a normal drop, but during validate ,loss is always some value, prec1 also keep zero. do you met this problem？

[JiyueWang]

I have no problem on the cifar10 dataset, but I got the same problem as you when transfer to my own local data. Have you solved the problem?

[JiyueWang]

I have solved my problem. The reason is the trainset is not shuffled before split it. Shuffle the indices before split indices = list(range(n_train)) shuffle = 1 if shuffle: np.random.seed(42) np.random.shuffle(indices) train_sampler = torch.utils.data.sampler.SubsetRandomSampler(indices[:split])