Junyang Lin
Junyang Lin
Hi, I think it is because of the recent PRs for inverting the masks. I just tried your case, and it really output "a" (lol...), and after my update (also...
I guess you would like to express features for each object and the text? It is not easy to do so. As you see in our framework, it is essentially...
Bug fixed. Have another try?
Oh, prompt tuning has now been merged to the main branch. I should delete the feature branch now.
My bad. Merge done now. Check the latest PR and you'll the change in the position of the assertion. You mean the detailed instruction of downstream tasks? Have you check...
try `--cpu`?
You are using multiple cpu device?
I've never done this before, and I am actually not sure about this... But seemingly you are using one device, and I believe there is no necessity to specify torch.distributed.
https://discuss.pytorch.org/t/how-to-use-multi-cpu-or-muti-cpu-core-to-train/147124/5 See if it helps
Not yet for now, sorry:( Will speed it up...