/usr/lib/python3.7/site-packages/torch/jit/_trace.py:754: UserWarning: The input to trace is already a ScriptModule, tracing it is a no-op. Returning the object as is.

[claire199705]

import torch from PIL import Image

img = Image.open('hen.jpg') model = torch.hub.load('hankyul2/EfficientNetV2-pytorch', 'efficientnet_v2_s', pretrained=True, nclass=1000)

import matplotlib.pyplot as plt from torchvision import transforms

transform = transforms.Compose([ transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]) x = transform(img).unsqueeze(0) model.eval() trace_model = torch.jit.trace(model, x) torch.jit.trace(trace_model, "./efficientnet_v2_s.pt") print("Successfully save traced model")

torch jit trace出现问题