I am deleting some layers of Resneet152 for example del resnet152.fc and del resnet152.layer4 and save it locally in order to get the dimension of 1024. Later when I import this saved model it complains about the missing layer4. What might be the the reason? Does still try tp access the original model. How can get 1024 feature vectors for a given image using Resnet1024.

[pradeep10kumar]

❓ Question

What you have already tried

Environment

Build information about Torch-TensorRT can be found by turning on debug messages

• PyTorch Version (e.g., 1.0):
• CPU Architecture:
• OS (e.g., Linux):
• How you installed PyTorch (conda, pip, libtorch, source):
• Build command you used (if compiling from source):
• Are you using local sources or building from archives:
• Python version:
• CUDA version:
• GPU models and configuration:
• Any other relevant information:

Additional context

[apbose]

Could you please provide more details on what error you are currently seeing and the model?

[github-actions[bot]]

This issue has not seen activity for 90 days, Remove stale label or comment or this will be closed in 10 days