Details of training base feature extractor (src/utils/train_image.py)

[Qingzhang1994]

When I trained the code, I found that the function required by the following code were missing. Could you please provide the code to help me study?
weights = torch.DoubleTensor(utils.class_weights(tr_clss)) in line 116
acc = utils.accuracy(op.data, cl.data, topk=(1,)) in line 276.

I found some functions to calculate accuracy, but after training an epoch it appears that the training set has 99% accuracy and the verification set has 0% accuracy.