j-marple-dev / ayolov2 Goto Github PK

I want to test training results.

but i dont know how to test training results.

can i get some advise?

i do not quite understand how to use a yolov5 representation learning model of coco ? it supposed to be a pretrain model like imagenet pretrained?

Hello, there is an error in the training custom dataset. The training is soft teacher.

The class does not change during model training using custom data.
Please tell me how to solve this problem.

We hear that YOLOX shows a quite good performance over anchor-based YOLO.
It would be worth to add YOLOX model support.

Reference: https://github.com/Megvii-BaseDetection/YOLOX

An index error occurred during training. May I know the reason?

Hi, thanks for your sharing.
When I tried to use multi-gpu to train Knowledge Distillation:
python3 -m torch.distributed.run --nproc_per_node $N_GPU distillation.py ...
I got the error:
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
distillation.py FAILED
Failures:
<NO_OTHER_FAILURES>