Hi, I am training VGG11 on a custom image dataset for 3-way 5-shot image classification using MAML. I am encapsulating the whole VGG11 model with MAML, i.e., not just the classification head. My hyperparameters are as follows:
Meta LR: 0.001
Fast LR: 0.5
Adaptation steps: 1
First order: False
Meta Batch Size: 5
Optimizer: AdamW
During the training, I noticed that after taking the first outer-loop optimization step, i.e., AdamW.step(), loss skyrockets to very large values, like ten thousands. Is this normal? Also, I am measuring the micro F1 score as accuracy metric of which curve for meta training/validation is as follows:
It is fluctuating too much in my opinion, is this normal?
I figured it out. I was using VGG11 with vanilla BatchNorm layers from PyTorch which was not working properly in meta training setup. I removed BatchNorm layers and now it works as expected. Thanks...
Hi, I am training
VGG11
on a custom image dataset for 3-way 5-shot image classification usingMAML
. I am encapsulating the wholeVGG11
model withMAML
, i.e., not just the classification head. My hyperparameters are as follows:During the training, I noticed that after taking the first outer-loop optimization step, i.e.,
AdamW.step()
, loss skyrockets to very large values, like ten thousands. Is this normal? Also, I am measuring the micro F1 score as accuracy metric of which curve for meta training/validation is as follows:It is fluctuating too much in my opinion, is this normal?
Thanks.