search

KushajveerSingh / resize_network_cv

PyTorch implementation of the paper "Learning to Resize Images for Computer Vision Tasks" on Imagenette and Imagewoof datasets
Apache License 2.0
57 stars 11 forks source link

Critical Bug: Resizer Outputs Original Image #2

Closed bilzard closed 3 years ago

bilzard commented 3 years ago

I found this bug by printing model summary. The model should return out instead of x (the original input image).

https://github.com/KushajveerSingh/resize_network_cv/blob/main/src/models/resizer.py#L76

bilzard commented 3 years ago

Close this issue because it duplicates #1.