Closed whysetiawan closed 1 year ago
My Source code is here version 16 (before i made changes)
Just took a quick scan, great job taking it to kaggle!
scale=16.0
for arcface
as a start, larger one may hard to converge.SGD
, you may start with a larger lr like 0.1
.weight_decay
is crucial for arcface
loss. You may add l2_regularizer
to model, or use optimizers like tfa.optimizers.SGDW
or tfa.optimizers.AdamW
.May try some tests myself if got some time, but not sure...
Thanks for your response. I'll make some changes and will be back if face another problem. Just a question, how many epochs does it usually take to train from scratch? I read Training Scripts and your result is always high at the first epochs.
Ya, For MS1MV3 dataset, it should give some reasonable result after first expoch. Not sure for CASIA datasets, as it's much smaller, but shouldn't be larger than 3 epochs.
Hi Thanks for providing this tutorial All from scratch. I have been following step by step and using Casia WebFace Datasets and the training progress increasing so slow.
Here is my accuracy result
First i was using LR: 0.0001 and change to 0.001 at 25 epochs in order to improve accuracy. It didn't help, i wonder if you have advice