Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Training #1

Open
tanakataiki opened this issue May 6, 2018 · 3 comments
Open

Training #1

tanakataiki opened this issue May 6, 2018 · 3 comments
Labels
enhancement New feature or request help wanted Extra attention is needed

Comments

@tanakataiki
Copy link
Owner

As I customed ssd for relatively log time.
I found it pretty hard to train by means of hyper parameter setting and sensitivity of architecture.
If your have environment to train then Upload your weights is very welcome let's make it better.
@tanakataiki tanakataiki added enhancement New feature or request help wanted Extra attention is needed labels Jul 9, 2018
@algila
Copy link

algila commented Nov 17, 2018

Hi,
may I recomment the users uploading their weights in folder "YourFineTunedWeights" to communicate also the dataset used doing training ? It should be beneficial for the other users doing Transfer learning with those.

@tanakataiki
Copy link
Owner Author

It's good idea.

@E12dward
Copy link

E12dward commented May 2, 2019

hi,i just train my model SSD300shufflnetV2 by following your strategy in SSD_train.ipynb ,but it seems hard to converge to a low loss (loss=4) .
is there something wrong?
thanks for your help

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request help wanted Extra attention is needed
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@algila @E12dward @tanakataiki