Damien Menigaux
Damien Menigaux
And labels of shape [class, t_start, t_end]
See the https://github.com/hyperfraise/end-to-end-BSN.pytorch/blob/master/example.py file for demo on how to use it.
Custom datasets will have the particularity of having custom dataloader and custom formats of data storage, label storage etc... So I thought that the only thing I could actually do...
Hey. i'll respond to issues on my code, on the aforementionned repo. If you've got suggestions, I'll be glad to adress them there. I don't think here is the best...
Yes I failed to go above baseline accuracy. But I never could with temporal detection framework anyways :/
I trained it fully end to end with 2d resnet 18 feature extractor with the code I linked. So I extracted features on the fly.
The problem is still happening. is there any fix ?
Hi. I'm experiencing the same issue. Would you care to exlain "replacing closures with classes with a call method solved the problem" ? I would very much like to be...
I'm very interested in this too
> Thanks for your contribution, and sorry about the long delay in reviewing this. > > Gitlab CI link: https://gitlab.tiker.net/inducer/pycuda/-/commit/c08a582c48d1b28e201adb0b2f5a1adec1f5eef6/pipelines?ref=issue_319 Do you know how to solve this ? ``` src/wrapper/wrap_cudadrv.cpp:1202:87:...