Set no of workers to 0
as for 5 it is showing BrokenPipeError: [Errno 32] Broken pipe

But getting this error:

File "D:\Project\Image extraction\Data-Augmentation-using-Deep-Convolutional-GAN-master\Data-Augmentation-using-Deep-Convolutional-GAN-master\train.py", line 161, in
train()

File "D:\Project\Image extraction\Data-Augmentation-using-Deep-Convolutional-GAN-master\Data-Augmentation-using-Deep-Convolutional-GAN-master\train.py", line 99, in train
label = torch.full((b_size,), real_label, device=device)

RuntimeError: Providing a bool or integral fill value without setting the optional dtype or out arguments is currently unsupported. In PyTorch 1.7, when dtype and out are not set a bool fill value will return a tensor of torch.bool dtype, and an integral fill value will return a tensor of torch.long dtype.

New to this area, not easy for me to train.
I found it coundn't work if your default config is used.