After training a model for several epochs, i save the model and will load it then for further evaluation. During inference (after loading) the model does not perform as well as it did during training.
I am setting the model to eval() mode and i have
torch.backends.cudnn.deterministic = True
torch.manual_seed(999)
np.random.seed(0)
in both parts of my code. Any ideas what i might be doing wrong?