Open JudyYe opened 6 years ago
Hi,
I observed a weird memory growth when I set the TEST.SCALE down from 800 to 600 or 200, consuming memory 872MiB(800), 1504MiB(600), 3035Mi(200).
The default config is configs/baselines/e2e_faster_rcnn_R-50-C4_1x.yaml with python3.6, Telsa K40, single GPU.
configs/baselines/e2e_faster_rcnn_R-50-C4_1x.yaml
It happens to me in both training and inference time. You might want to reproduce as :
python tools/infer_simple.py \ --dataset coco \ --cfg configs/baselines/e2e_faster_rcnn_R-50-C4_1x.yaml \ --load_detectron data/pretrained_model/faster_r50_coco.pkl \ --image_dir any_image_dir/ \ --output_dir $output \ --set TEST.SCALE $SCALE
Does anybody else have a similar result? Any clue why this happens?
Thank you.
The GPU memory consuming is strange for me too.
Hi,
I observed a weird memory growth when I set the TEST.SCALE down from 800 to 600 or 200, consuming memory 872MiB(800), 1504MiB(600), 3035Mi(200).
The default config is
configs/baselines/e2e_faster_rcnn_R-50-C4_1x.yaml
with python3.6, Telsa K40, single GPU.It happens to me in both training and inference time. You might want to reproduce as :
Does anybody else have a similar result? Any clue why this happens?
Thank you.