Open lewis-v opened 9 months ago
Currently we run out of our founding for renting server to train models with large input size. So the priority for developing new big models is not high. However, the code support to train p7-1280 and p7-1920 models.
What configuration commands or configurations are used to train p7-1280 and p7-1920?
Hi @WongKinYiu, would you please share the p6-1280 config file, I will train it and share the model weight back in the repo. I have two RTX 6000 ADA, it will take some time to train. But it's interesting to see the p6-1280 model performance.
I have seen the corresponding configuration in the project, but yolov9 does not seem to support it yet. Is there a plan for support, or how to use P7