best way to save a pytorch model architecture not weight code example

Example 1: pytorch save model

Saving:
	torch.save(model, PATH)


Loading: 
	model = torch.load(PATH)
	model.eval()
    
A common PyTorch convention is to save models using either a .pt or .pth file extension.

Example 2: how to save a neural network pytorch

Saving:
	torch.save(model, PATH)


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