Arthur Douillard

I was using 2 V100 GPUs. Do you also use the same batch size as me? I know that the mixed precision could something give different results depending on the...

Hey, Sorry I cannot respond ealier, I'm a busy right now with the writing of my thesis manuscript. 1. I'm not sure about your results as when I gave you...

After cleaning the code I've only tested for cifar 50 steps where results where exactly reproduced. I'm re-launching 10 steps to check that.

Hey, so I haven't time to full reproduce 10 steps with a single GPU but the first 5 steps are indeed like yours. While when runned with 2 GPUs, I...

Hum... I'm launching experiments with batch size of 256 (the yaml that I gave you only did it for step t>1 not t=0 my bad), with a LR of 0.0005...

Hello, I'm still trying to improve perfs on a single GPU. I'll keep this issue updated if I find ways to do it. In the mean time, try running on...

Yeah, I chatted with Hugo Touvron (the DeiT main author) and he also suggested RA. I've tried multi-gpu without RA and single-gpu with RA, and nothing significantly changed. I'll keep...

Accuracy variation is in major part explained in the following [erratum](https://github.com/arthurdouillard/dytox/blob/main/erratum_distributed.md). We are trying to see how we could emulate our distributed memory (see erratum) in the single GPU setting.

Hey! I think we would need a new kind of taskset, and a new scenario. I'm not super familiar with continual object detection, but I assume it's similar to continual...

Hum... I'm not very well aware of the scenarios in Continual Object Detection, but if we assume they are like the scenarios in segmentation (namely sequential, disjoint, and overlap): -...