Pramodith
(Pramodith Bprum)
May 19, 2020, 7:54pm
1
Hi,
I’ve trained a custom transformer model and followed this to save a quantized model.
However when I try to load the model using
model.load_state_dict(torch.load('path'))
I receive the following error:
Missing key(s) in state_dict: “xxxxx.weight”,
Unexpected key(s) in state_dict: “xxxx.scale, xxxx.zero_point, …”
It looks like the names of the original parameters of the model have been changed. Can anyone help with how I can resolve this error?
While loading the model is the model
now a quantized model? If you convert the model to quantized model and then load the quantized state_dict it should work.
Pramodith
(Pramodith Bprum)
May 21, 2020, 3:44am
3
I’m not sure that I understand, assuming class A inherits from nn.Module and corresponds to the architecture of my dnn.
model = A()
is essentially all I do. Do I need to do anything to quantize it?
Pramodith
(Pramodith Bprum)
May 21, 2020, 3:46am
4
Ok I think I get it now, I have to do something like this after
model = A
quantized_model = torch.quantization.quantize_dynamic(
model, {torch.nn.Linear}, dtype=torch.qint8
)