While the num_classes isn't 1000 , some error in sample.py!

Q1:when using single gpu train model , model.module is not available Q2: sample.py y_null = torch.tensor([1000] * n, device=device) should be y_null = torch.tensor([args.num_classes] * n, device=device) Q3:after training,i use my trained model to generate data,the sample.png looks like a gauss noise,my train loss is below 0.05! but i cant use this model !