Why does the validation set accuracy fluctuate when I train ImageNet-1k?

52 views Asked by At

I am training ImageNet-1k using a CNN model built by myself. The training configuration is as follows:

  • Optimizer: AdamW
  • Learning rate: 4e-5
  • weight decay: 0.1
  • data augmentation: random crop + horizontal flip
  • batch size: 256
  • GPU: 4x 2080Ti

The accuracy of training and validation is shown in the figure below: enter image description here I was wondering if anyone has had this kind of validation set accuracy oscillation? What is the solution?

I tried setting drop_path=0.2, but still have similar problems. I'm a novice, so I don't have many solutions. If anyone can tell me the reason or solution of this phenomenon, I will be very grateful.

0

There are 0 answers