Frédéric Branchaud-Charron
Frédéric Branchaud-Charron
Hello, Thank you for your question. Object detection is a tricky problem in active learning and hasn't been studied extensively. Niko Sünderhauf made quite a lot of contributions to the...
Using mkdocs-material I can get this type of look. What do we think about it? @parmidaatg @GeorgePearse . Once we have a new logo, we can switch it up as...
I made a lot of work on the branch `docs/mkdocs`, would appreciate if someone would run it locally and give some feedback. I'll continue next week.
Maybe `poetry clean --all` ? and then `poetry install`? Otherwise, the new deps are ; ``` # Documentation mkdocs-jupyter = "^0.21.0" mkdocs-material = "^8.3.6" Pygments = "^2.12.0" mkdocstrings = {extras...
Forgot to commit the symlink to `notebooks`. just fixed many issues as well.
Reference: Active Learning for Convolutional Neural Networks: A Core-Set Approach, https://arxiv.org/abs/1708.00489 https://arxiv.org/pdf/1910.08707.pdf
No we didn't worked on this. Yes that would be amazing if you could get the ball rolling on this. We will be there to help that's for sure!
Hello, I tried to make this work [in this gist](https://gist.github.com/Dref360/4fa7d6a807901145570bb02238b674cf), but the `predict_on_batch` doesn't work yet. If we run `model(data)` n times, we would get the following output: ``` [...
Anything I can help with? Happy to schedule a meeting as needed.
Hi george, Oh that looks very cool!! So what would be the project look like? Would we run many experiments on many datasets and BaaL's website would refer to these...