Ning Li
Ning Li
The trained models of RTS and STA can be found at [this url](https://drive.google.com/drive/folders/1uMQqeRN4RbaeF3IsRpvjvk6D5K8khpSW). **--Maybe this one is ok for your usage.** I just used them(the pth & pth.tar) to test...
Hi, I have fixed it by this way: you can add this line: self.blocks.cuda() in the __init__() of the MaxViTStage class to have a try.
**Yes, I have the same question.**
**yes, I also have the question that how can we get the patch number in your Head (of the Stage1) ?**
Hi, you can see the detail of the dist_train.sh script, and then you can just run the main.py script with some parameter. have a try
> Hi @mywebinfo65536. This is a bit strange, it looks like missing data that the sampler tries to load. Is it reproducible ? Could you tell me what's the size...
By the way, could you tell me the trainning speed (FPS: 6-8) is right? I just felt it a bit low in my trainning.
> @mywebinfo65536 do you have any further issues ? Or is it working for you now ? Hi mattpfr, thanks for your reply, I now have no further issues, but...