josht000
josht000
@BradNeuberg Heyy, thanks for sharing the output of your runs, but I'm still having issues with the cocostuff27 data. Would you mind dropping in your train_config.yml? Also, are you running...
@Chilicyy Been waiting patiently for this capability. Any updates?
@jahongir7174 I see that reference and would you say that they basically lied?
@jahongir7174 I commend you on your research skills! Diving through those links helped. It's too bad Ultralytics hasn't put together a whitepaper for their work. Someone could probably do that...
@fingerthief very nice! Will check it out soon. Thanks.
Would using the proxy feature, and a good proxy that's not also limited, get around this?
OK. Um i guess illl have to try it.
Having the same issues. I commented out the VITEmbedding and the things in evaluation/__init__.py to get through it and then ran run.py by specifying the clip encoder: `python run.py pretrain...
Ok, I was going to go down the road of adjusting the hparams of LR, epochs, and LR like as if it was a standard training run. I didn't see...
@levipereira I uncommented the line you suggested and looking at the results again. I now see the the QAT model is essentially on par with the "origin" model. BUT the...