When doing image classification, what can someone do to increase accuracy? I have 20,000 images
I am using a pretrained model (senet154), but I’m only getting 87 percent accuracy. what else can be suggested to increase accuracy other than more images and better quality of images.
Thanks!
For some tips or inspiration check out this thread: https://forums.fast.ai/t/how-we-beat-the-5-epoch-imagewoof-leaderboard-score-some-new-techniques-to-consider/53453
You can try different kind of weight initialisations.
Eg: Xavier , He etc.
You can also augment the data.