Closed seekingdeep closed 3 years ago
I think you could try the original resolution. Storing the image tensor on the disk and then modify the data loader to restore the tensors from the disk is a good solution when running the get_real_stat.py
is a good solution and deserves a trial.
@lmxyy @junyanz Hi there,
i am trying to use pix2pix to train an instance segmentation model, My input images that are used in training are
256*256
crops of my original1024*1024
images.The issue is that:
if using
256*256
crops in training, the model is not converging and thefid
is somewhat bad. Because the256*256
crops are too small, and the information of the "big picture" is somewhat lost.When trying to using the original
1024*1024
, it requires high memory when runningget_real_stat.py
.Possible solution: # 44 is to store the image tensor on the disk and then modify the dataloader to restore the tensors from the disk.
i think using the HD original images
1024*1024
in training should get better results, Waiting for your replyiteration 185000, Prediction:
Groundtruth: