Santosh Shriyan

I am already trying it out... unfortunately the lowest rtx 30 series goes to is 460 driver which is cuda 11.2. That becomes a problem.

> Hello Everyone, I haven't worked with Docker before trying to use this tool. I followed all the installation steps from docker and COCO-Annotator both on Linux and Windows and...

@violamarconetto you solved the sharp results issue? Also can you share the exact changes made to achieve the 2x implementation.

@Liang-Rui Did you figure out why is there a increase in loss, cause I'm facing the same problem.

Same here... I am stuck with data, meta and index files of the self trained model, with no means to use inference without ckpt file. I don't see the ckpt...