-
Notifications
You must be signed in to change notification settings - Fork 241
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Loss plateau detection #7
Comments
hi @dereyly can you share some experiences about how to set the plateau configurations? thanks. |
@dereyly How can i train in plateau mode? |
Hi, Let me answer @dereyly 's question one by one
|
@sanghoon Dear sanghoon, I wonder why you set the "plateau_winsize" are doubled every x/10 LR ? plateau_winsize: 10000 suppose that here lr=0.01 another confuse: if plateau_winsize is 40000, does it means that we at least do 40000 iterators training(using the same lr 0.0001) regardless of the training loss "decrease/not decrease"? |
@sanghoon Thank you! but learning process not finished now |
Hi @xiaoxiongli, Answering your second question. |
@zimenglan-sysu-512 |
@sanghoon thank you very much! I got it~^_^ @zimenglan-sysu-512 @dereyly when i use plateau training mode(VOC2007), the mAP is 0.6983, when i do not use this mode, the mAP is about 0.714. totally iterators = 20w. train_net: "models/pvanet/example_train_384/train.prototxt" base_lr: 0.001 display: 20 We disable standard caffe solver snapshotting and implement our own snapshotfunctionsnapshot: 0 We still use the snapshot prefix, thoughsnapshot_prefix: "pvanet_frcnn_384" |
Hi all, One more thing... If you want to train a network with 'plateau', ImageNet pre-training (1000 class)
COCO + VOC2007 + VOC2012 (80 class)
VOC2007 + VOC2012 (20 class)
|
@sanghoon Thank you. |
Hello!
Sorry if my question is off-top.
Many interesting things i think about when read your paper.
One of this thing how to train own architecture from scratch
And idea to detect plateau is good. And you write that gives significant improvement. I analysis my graphics of accuracy and i want to try create "plateau detector".
I know that you use inhouse library. But maybe you give some advice how to create it in Caffe:
The text was updated successfully, but these errors were encountered: