MCPcopy Create free account
hub / github.com/KeepTryingTo/Pytorch-GAN / load_checkpoint

Function load_checkpoint

pix2pix/utils.py:41–50  ·  view source on GitHub ↗
(checkpoint_file, model, optimizer, lr)

Source from the content-addressed store, hash-verified

39
40
41def load_checkpoint(checkpoint_file, model, optimizer, lr):
42 print("=> Loading checkpoint")
43 checkpoint = torch.load(checkpoint_file, map_location=config.DEVICE)
44 model.load_state_dict(checkpoint["state_dict"])
45 optimizer.load_state_dict(checkpoint["optimizer"])
46
47 # If we don't do this then it will just have learning rate of old checkpoint
48 # and it will lead to many hours of debugging \:
49 for param_group in optimizer.param_groups:
50 param_group["lr"] = lr

Callers 1

mainFunction · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected