-
Notifications
You must be signed in to change notification settings - Fork 59
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
Testing framework on THUMOS #21
Comments
Sort of? I can get similar results to the original using the TF code that @wzmsltw sent (see below). However, trying to turn that into Pytorch has proven oddly difficult to match. This is using the TF code: This is using the pytorch code translated to use Thumos: |
Update: I now have this reproducing in pytorch as well. |
I'm also interesting in the thumos14, any update so far? |
Hi @cinjon, you seem to have succeeded in coding the thumos14 version. I'd like to do some statistics on the results. Is it possible for you provide me the .txt file having the results in? |
Hi, i unfortunately don't have much time to help others atm because i'm trying to submit my own CVPR paper next week. |
Hi @cinjon , I'm trying to do some work on THUMOS14, can you share me the code in THUMOS14 version? Maybe just data preparation. |
Hello, @tobiascz Thanks for this good question. And I am also confused by applying BSN to a customized dataset. The biggest question of me is, which exact layer of the output of TSN should I keep, in order to train the BSN? PF |
@cinjon can you share the PyTorch code for THUMOS 14 that you used to reproduce the results |
Hello, |
Hi, have anyone received the code yet? Can you also send it to me? Thank you in advance. |
@cinjon how is your progress to try this code on THUMOS?
If I understand this correctly I have to extract the snippet level features using TSN (https://github.com/yjxiong/anet2016-cuhk). But the anet2016-cuhk is pretrained on activity net so you first have to finetune the network on THUMOS and then extract the snippet level features from THUMOS and do the TEM, PGM & finally the PEM training? Is this correct?
Originally posted by @tobiascz in #12 (comment)
The text was updated successfully, but these errors were encountered: