LemonWei111

Encountering "Expected to have finished reduction in the prior iteration before starting a new one" Error During Training

7

I'm encountering an issue while attempting to finetune a model on my dataset. I run the command as follows: `torchrun --master_port=7777 --nproc_per_node=1 train.py -c configs/deim_dfine/deim_hgnetv2_l_coco.yml --use-amp --seed 42 -t deim_dfine_hgnetv2_l_coco_50e.pth`...

config for num_classes

7

I am confused that do we need to set the background as a class. Cause most models for object detection like YOLO and DETR set num_classes to the original number...

predict_boxes not match (xyxy)

1

Why there will be predict_boxes not fit (boxes[:, 2:] >= boxes[:, :2]).all() **sometimes** even when I set seed. Is this my mistake of train data or a bug?