Hello.
I have trained a model using Quantization Aware training and saved the model using
- tsmodel = model.to_torchscript()
During loading, I use the below code.
import torch
tsmodel = torch.jit.load(‘model_script.pt’,map_location=‘cpu’)
tsmodel.eval()
tsmodel.model.conv1(tsmodel.quant(torch.ones(1,3,224,224))
I am getting the below error.
Please help me with the above error.