bhack
bhack
I think that fedarated and continual learning are more relevant in the on device/edge use case cause, in this context, It is still hard to achieve few-shot/zero-shot learning of "general...
About changing the model in training mode check: https://discuss.tensorflow.org/t/how-to-implement-layerdrop-in-tensorflow-transformers/2396
We had already some research work at ICML 2021 to joint Federated and Continual learning with a TF reference impl: https://github.com/wyjeong/FedWeIT It could be nice to open this research subdomain...
Is this finalized/approved? https://blog.tensorflow.org/2021/11/on-device-training-in-tensorflow-lite.html?m=1
Another interesting use case, also if Imagenet probably It is a too large dataset for many edge computing TFlite platforms, Is this recent Deepmind paper `One Pass ImageNet`: https://arxiv.org/abs/2111.01956
Is this project still in active development/progressing on the roadmap? It Is quite strange that It was not mentioned in the next Neurips 2020 workshop https://montrealrobotics.ca/diffcvgp/ but I see that...
https://github.com/NVlabs/nvdiffrast.
Can we specify this? Cause sometimes 3d data augmentation means also synthetic datasets. I.e. 3d dataset where you need to augment inside a minimal 3d engine (opengl, vulkan) for camera,...
Is this a CV only metric?
> Curious, if it's general, what should be the approach to include this? I don't know https://github.com/keras-team/keras-cv/pull/30#issuecomment-1008685239