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

Function load_checkpoint

StyleGAN/utils.py:68–77  ·  view source on GitHub ↗
(checkpoint_file, model, optimizer, lr)

Source from the content-addressed store, hash-verified

66
67#加载模型
68def load_checkpoint(checkpoint_file, model, optimizer, lr):
69 print("=> Loading checkpoint")
70 checkpoint = torch.load(checkpoint_file, map_location="cuda")
71 model.load_state_dict(checkpoint["state_dict"])
72 optimizer.load_state_dict(checkpoint["optimizer"])
73
74 # If we don't do this then it will just have learning rate of old checkpoint
75 # and it will lead to many hours of debugging \:
76 for param_group in optimizer.param_groups:
77 param_group["lr"] = lr
78
79
80def seed_everything(seed=42):

Callers 1

mainFunction · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected