How to avoid overfitting

Hello,
ZheDong, thanks for you sharing such a good work. I want to reproduce it in Pytorch,but I'm sorry that I encountered the overfitting problem.
To get the results quickly, I randomly choose 10,000 samples as traindata and 1,000 as valdata, 1,000 as testdata separately. Finally I got about 100% recall@5 on the training set while only half of it on the val data.
And I'm a fresh man to ImageTextEmbedding,could you share some solutions to that. I guess there are relevant reasons:

1. Data normalization. I don't compute the mean and var of train_data explicitly, and just divide it by 255, subtract 0.5, and thendivide it by 0.5

2. L2 regularization. I just use the 1e-5 regularization intensity

3. The complexity of classifier. After generator, I add a classifier with a softmax layer directly. Whether more fully connection layers can slow down the fitting of the training set

Finally, I want to ask how to mine the hard triplet online in Pytorch efficiently.

Thanks.

No repository file, test, or entry point is identified. Start by reviewing the PyTorch training setup and the stated train, validation, and test split, then establish what change would address the reported overfitting and how online hard-triplet mining should be evaluated.