Kirill Koncha

Thank you for answer! I included different languages data along with new language (I fit 19 languages into the model, e.g., French, English and Kyrgyz, which was not represented in...

I ensured that every batch contains all languages I want to detect and fine-tuned model, it worked pretty fine. Thanks a lot!

> Hi all, I've found that the `sigmoid + norm` in the decoder will cause the NaN error when FP16 is enabled. In the latest update, we provide a special...

> Hi @siddagra, thanks for your interest in SparseInst! > It seems that FP16 cannot support deformable conv in detectron2, I'll check it soon. Hello again! Did you find anything?...

@Vincent630, maybe you could help?

So, I should add registration in `train_net.py`, change names in the config and then just run `train_net.py`? Or some other changes are need to be done as build_evaluator description suggests...

Thanks a lot for your answer! I also have one last question: when I training model on my own dataset, which have different new classes, should I use somehow already...

And how I can change` NUM_CLASSES`? I can't find this in base config, only in the training script. Or it will be done automatically based on the number of classes...

Okay, thanks!!! But why `Base-SparseInst.yaml` does not have this parameter originally?

Thank you a lot! Could I ask one more question: is there any way to specifies the numbers of eight gpu's I want to use? (For example, I want to...