I trained a dataset (grey-scale ultrasound images. with 15 classes) on
vgg-16 gives me a validation accuracy of 92% where as I can only hit 83% with
I handled overfitting in both architectures with dropout in FC layer and regularization in optimizer.
I don’t know why there would be minimal overfitting with
vgg and not
resnet . The
resnet model train loss is 0.02 vs valid loss 0.67. Moreover
resnet model doesn’t seem to improve beyond this loss range. I have tried hyper-parameter tuning on weight decay, learning rate, momentum, dropout.
The purpose of this exercise to improve our predictions on the dataset. Hence I started trying
I would love some suggestions on
- How to improve
resnet-34performance and address its overfitting.
- Any other architecture suggestions that would work for this type of dataset.