Test accuracy lower with higher batch size

[agirbau]

Hello! I was testing a trained model, and found that the testing accuracy reported by the code is lower for bigger batch sizes.

For instance: python testing.py --test $TEST_PATH--checkpoint log/model_best_caltech101.pth --batch_size 12 --num_workers 12 reports:

While: python testing.py --test $TEST_PATH--checkpoint log/model_best_caltech101.pth --batch_size 48 --num_workers 12 reports:

Any idea why this might be happening?

Edit: It gets weirder, as running again the evaluation reports different accuracies (all tested with --batch_size 48). Run 1:

Run2:

Run3: