why FeTrIL acc is so bad about pycil HOT 10 CLOSED

from pycil.

It seems that you failed at the base training stage, did you wrongly modify the code for base training?

from pycil.

It seems that you failed at the base training stage, did you wrongly modify the code for base training?

yes, In line 104: https://github.com/G-U-N/PyCIL/blob/master/models/fetril.py#L104

I removed this line's comment, otherwise an error will be reported

from pycil.

your training log?

from pycil.

your training log?

sorry, it lost. please wait 10 minutes

from pycil.

sorry

final result:

2022-12-19 13:51:09,278 [trainer.py] => CNN top1 curve: [80.42, 71.2, 66.36, 62.06, 59.57, 56.16]
2022-12-19 13:51:09,278 [trainer.py] => CNN top5 curve: [96.72, 91.63, 89.34, 87.46, 85.46, 83.33]

I had set all BN layers : track_running_stats=False, so acc is bad. set track_running_stats=True will got good performance.

so, why does this happen, in order to compare my algorithm fairly, I should set track_running_stats=False for all BN Layers.

from pycil.

Glad to see you have reproduced the ideal results in our framework.

For your question:

Setting track_runing_stats to False will cause the running_mean and running_var being frozen, which typically makes the optimization in CNNs much harder especially when training from scratch. You'd better learn more about how BN works in neural networks.

from pycil.

wait.....

look this repo(task increment learning): https://github.com/sahagobinda/GPM/blob/main/main_cifar100.py

all of BN layers are set track_runing_stats to false, but got good performance.......

maybe this is another question?

from pycil.

I have no responsibility to answer questions outside our framework, thanks.

from pycil.

I'm sorry I was negligent

from pycil.