Pytorch-ONNXを量子化して高速化する - Qiita

import torch model = torch.hub.load("bryandlee/animegan2-pytorch:main", "generator", pretrained="celeba_distill").eval() model_int8 = torch.quantization.convert(model) dummy_input = torch.randn(1, 3, 512, 512) input_names = [ "input" ] output_names = [ "var_444" ] torch.onnx.export(model_int8z, dummy_input, "animegan2_celeba_distill.onnx", verbose=True, input_names=input_names, output_names=output