kienduynguyen/BoxeR

Evaluation Results AP=0

Opened this issue · 1 comments

351246241 commented

Thank you for share this work!
I use python tools/run.py --config e2edet/config/COCO-InstanceSegmentation/boxer2d_R_50_3x.yaml --model boxer2d --task detection fortraining in coco dataset.
then,I evaluate coco dataset with python tools/run.py --config e2edet/config/COCO-InstanceSegmentation/boxer2d_R_50_3x.yaml --model boxer2d --task detection training.run_type=val.
But I get AP =0,like this
image
I assumed it was a training error on my part and then downloaded the provided pre-training weights. But got the same result
python run.py --config e2edet/config/COCO-InstanceSegmentation/boxer2d_R_101_5x_lsj_resmode_v2.yaml --model boxer2d --task detection training.run_type=val
image

kienduynguyen commented

Sorry for the confusion! You should also specify the model path for the pre-trained checkpoint:

python run.py --config e2edet/config/COCO-InstanceSegmentation/boxer2d_R_101_5x_lsj_resmode_v2.yaml --model boxer2d --task detection training.run_type=val training.resume=True training.resume_file=<PATH_TO_CKPT>