Kunyang Zhou
Kunyang Zhou
您好,我训练过程中发现MM-Grounding DINO显存在不断增加,我清楚Randomchoice resize可能是导致这个原因,但是为何batchsize=2,memory=12866,3090的24GB显存会溢出呢。我看训练过程中GPU的memory不断增加,这是什么原因?
基于project里面提供的train.py运行以下代码 ``` python train.py \ --data-path /home/kunyangzhou/project/dataset/coco \ --dataset coco \ --model retinanet_resnet50_fpn \ --batch-size 8 \ --pretrained \ --test-only ``` 然后出现报错 ``` Stack trace (most recent call last) in...
Hi, I have a question about training multiple detection formats jointly:Whether you choose a certain format like box or polygon to train the model in one training iter instead of...
华为昇腾910对Oneflow-lite适配,并修复其中一些bug。