Timothy Kassis

Results 10 issues of Timothy Kassis

I wanted to submit a pull request to add this, but not sure where to put it. I propose adding Label Distribution Smoothing (LDS) recently presented by Yang et. al...

enhancement
tutorial nb

Thanks for everyone who is developing this repo. Great work! Is there a 1-2 sentence description somewhere of what each of the pre-trained models on https://huggingface.co/seyonec are? I'm a bit...

Not an issue really, but I can't seem to find a clear answer to this online. Are there particular advantages to training on similar images? For example, if I wanted...

### Feature Description In Keras it's possible to plot validation loss by accessing it through model.history, but Auto-Keras does not return an object containing this when I call .fit. What's...

feature request
pinned

Thanks for putting out this paper, sounds very promising. Would you mind clarifying the number of iterations you use for self-supervised training. You mention in the paper that you use...

Thanks to everyone contributing to this repo. I'd like to suggest the addition of the new regression-focused contrastive loss from Dina Katabi's group at MIT. SupCR is focused on regression...

new algorithm request

Trying to train on single-channel grayscale images using '--img_ch 1' argument during training but I get the following error immediately after starting training: > ValueError: Trying to share variable generator_A/conv/conv2d/kernel,...

PEER looks like an interesting approach and thanks for implementing so cleanly! I do have a quick question though about recommended usage with x-transformers. Would something like this be a...

### Describe the bug Aggressive mode seems to be opposite of what it intends to do. Acceleration when the lead starts moving is extremely slow and the car tends to...

bug
car
toyota

### Describe the feature An interesting new bio benchmark that might be worth adding: https://github.com/science-machine/biomlbench ### Will you implement it? - [ ] I would like to implement this feature...