-
Notifications
You must be signed in to change notification settings - Fork 1.2k
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
Add triplet for training models #1529
Labels
kind/discussion
community discussion
Comments
could you please describe triplet in more details? |
font{
line-height: 1.6;
}
ul,ol{
padding-left: 20px;
list-style-position: inside;
}
I'd like to add triplet loss as a train loss, It is hoped that images with different angles of the same ID can learn similar features.
The source code I plan to use for Tripletloss is : torch.nn — PyTorch master documentation
***@***.***
…---- Replied Message ----
From
***@***.***>
Date
8/1/2022 18:16
To
***@***.***>
Cc
***@***.***>
,
***@***.***>
Subject
Re: [open-mmlab/mmpose] Add triplet for training models (Issue #1529)
could you please describe triplet in more details?
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: ***@***.***>
|
Maybe you can add a custom dataset to generate triplets. I am not sure. |
font{
line-height: 1.6;
}
ul,ol{
padding-left: 20px;
list-style-position: inside;
}
But how to deal with batch size. for I've read 'bottomup coco dataset' and it just catch data by function 'get_single', how mmpose load new data? like use forward or iter function? Could you please point the specific code files and line numbers? Thanks!
***@***.***
…---- Replied Message ----
From
***@***.***>
Date
8/1/2022 18:32
To
***@***.***>
Cc
***@***.***>
,
***@***.***>
Subject
Re: [open-mmlab/mmpose] Add triplet for training models (Issue #1529)
Maybe you can add a custom dataset to generate triplets. I am not sure.
—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you authored the thread.Message ID: ***@***.***>
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,If I want to add triplet for training how should I add it to the project in a reasonable way?
The text was updated successfully, but these errors were encountered: