pytorch/examples

Low training accuracy using pre-trained model

Open

#889 aperta il 4 mar 2021

Vedi su GitHub
 (2 commenti) (0 reazioni) (0 assegnatari)Python (9429 fork)batch import
help wantedvision

Metriche repository

Star
 (21.634 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

Hello, I am trying to evaluate a pre-trained mobilenetv2 model from torchvision on the ImageNet training dataset using this script. To do so, I modify lines 235-237 to perform validation on the train loader instead of the val loader:

    if args.evaluate:
        validate(train_loader, model, criterion, args)
        return

Everything else is left untouched. The command I use to run is: python imagenet_train_example.py -a mobilenet_v2 -j 16 -b 1024 -e --pretrained /data/ImageNet However, the results are lower than expected: Acc@1 2.926 Acc@5 15.079 Loss 11.795791

Guida contributor