Answers for "load checkpoint pytorch"

how to save a neural network pytorch

Saving:
	torch.save(model, PATH)


Loading: 
	model = torch.load(PATH)
	model.eval()

model load checkpoint pytorch

##this is how you load the model from the checkpoint

model = Net()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
loss = checkpoint['loss']

model.eval()
# - or -
model.train()

model load checkpoint pytorch

# Additional information
EPOCH = 5
PATH = "model.pt"
LOSS = 0.4

##this is how you save model checkpoint

torch.save({
            'epoch': EPOCH,
            'model_state_dict': net.state_dict(),
            'optimizer_state_dict': optimizer.state_dict(),
            'loss': LOSS,
            }, PATH)