Expected 4-dimensional input for 4-dimensional weight [64, 3, 3, 3], but got 3-dimensional input of size [3, 112, 112] instead

23

You definitely need to save your model…otherwise you get a model with random weights later on…

24

ok thank

so am i correct i need to put that code at the end of a code.

torch.save(net.state_dict(), 'my_model.pth')

and when i want to use it for test i need to use this code

model.load_state_dict(torch.load('my_model.pth'))
and test my model am i correct

25

is to load is thiswhile thing
model = TheModelClass(*args, **kwargs)
model.load_state_dict(torch.load(PATH))
model.eval()

just when i search in google it didnt say much so just want to make sure i do it right

26

Hi just wonder is it possible to tell me which line did you fix my code? just when i try to imprement again same error pop up