FewX
FewX copied to clipboard
fanq15
FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.
Hi~ I was trying to apply your fsod model to new dataset. But encounter some problems when registering dataset. I have read some documents about Detectron2, still got confused. So,...
Thanks for your great work, could you please release the code of your paper《Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation》?
When I apply the FewX on custom dataset, I meet an error: Traceback (most recent call last): File "/root/FewX-master/fsod_train_net.py", line 323, in launch( File "/root/.local/lib/python3.9/site-packages/detectron2/engine/launch.py", line 62, in launch main_func(*args)...
I do use my own custom coco dataset to train FSOD by 4 gpus (GTX 2080 ti). cost 2315 MB per GPU when trainning the model and works. but when...
Hello. I'm attempting to use a different dataset with the AttentionRPN. The evaluation script uses the pickled dataframe of the 10-shot novel classes, so when I evaluate, it detects only...
Hello, i test in coco_val with 64 images include 2 class.Like this for the query:  Then choose 2 ways-9shot, about _person_ and _TV_ like query img from '10_shot_support' dir....
Can I train directly with VOC dataset? Or do I need to convert VOC format to COCO format?
My graphics boards is gtx1660ti, memory 6G. I run this code to report an error: RuntimeError: CUDA out of memory. Tried to allocate 1.00 GiB (GPU 0; 5.81 GiB total...
When i use the command of "sh all.sh",it end with "============ Few-shot object detetion will start. =============",do you know what wrong with it ?
