How can we apply dropout after saved checkpoint?

Currently if I try I get an error as follows:

RuntimeError: Error(s) in loading state_dict for MobileNet:
	Missing key(s) in state_dict: "conv1.2.weight", "conv1.2.bias", "conv1.2.running_mean", "conv1.2.running_var". 
	Unexpected key(s) in state_dict: "conv1.0.weight", "conv1.1.bias", "conv1.1.running_mean", "conv1.1.running_var", "conv1.1.num_batches_tracked". 
	size mismatch for conv1.1.weight: copying a param with shape torch.Size([24]) from checkpoint, the shape in current model is torch.Size([24, 3, 1, 1]).

You are most probably messing up the saving and loading of checkpoint. Without code it difficult to tell what is causing the error.