Abe404 / root_painter

RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation
https://nph.onlinelibrary.wiley.com/doi/full/10.1111/nph.18387
Other
59 stars 17 forks source link

Evaluate 8 bit optimisers #95

Open Abe404 opened 1 year ago

Abe404 commented 1 year ago

If I can get RootPainter working with an 8 bit optimiser it could reduce memory requirements and speed up training.

See: https://arxiv.org/pdf/2303.10181.pdf who state: "The use of 8-bit optimiser reduces the GPU memory utilised and the convergence time. The more interesting observation is that in almost all cases (except ViT), it also converges to a better solution, yielding a small performance improvement." One concern is training stability. They also mention: "One reason for the degradation in performance in transformers when using the 8-bit optimiser could be instability during training."

See: Dettmers, T., Lewis, M., Shleifer, S., Zettlemoyer, L.: 8-bit optimizers via block-wise quantization. In: International Conference on Learning Representations (2022), https://openreview.net/forum?id=shpkpVXzo3h

https://github.com/TimDettmers/bitsandbytes