This repo is a implementation of the Foundation Model Assisted Weakly Supervised Semantic Segmentation. The code is developed based on the Pytorch framework.
when I run python src/tasks/aff_cam/run.py -P 0 -e 0 --cache_ori_cam 0 -c configs/VOC/cls/infer/final/affx2,at_score,att2affx1/cfg.py, I met this problemmatplotlib.get_backend()='agg' Dataset <VOCAug2>: #data: 10582 优化: 0批次 [00:00, ?批次/s] <class 'utils.cache_dir.CacheDir'>: CacheDir状态为未启用,terminate无效。.
what's the file in 'experiment/VOC/cls/infer/final/affx2,at_score,att2affx1/ann,affed/seed/2009_004108.png'?
How can I get this file? I knowed that you provided but how to produce this kind of images? And what's the meaning of these images?
bash tools/dist_train.sh configs/m2f_psudo/m2f-sl22-bt4-100k-512x-COCO.py 2
出现
FileNotFoundError: [Errno 2] No such file or directory: 'configs/m2f_psudo/m2f-sl22-bt4-80k-512x-VOC.py'
这个配置文件好像没有,可以提供下mmsegmentation的完整目录内容吗
I encountered some errors when installing dependencies. Since my computer is Windows system, I cannot install some dependencies. I would like to ask if you have “.yaml” files that can be installed on Windows. Thank you !
Hello author. Thanks for the wonderful work.
I want to download the data link, however I can't sign up for the baidu since I'm living abroad.(The sign up for the abroad user was closed)
So could you give us the new link for the reproduction?
Hello, thank you for your great work. Could you please tell me where the Multi-label contrastive loss in your paper is implemented? I really can't find it, thank you very much.
when I focus on stage 2, I use mmcv2.1.0 mmdet 3.3.0 mmengine 0.7.3 mmsegmentation 1.2.2 to train the segmentation network successfully. do u know why the error shown below occur when i test the segmentation network and how to solve it?
TypeError: class SegVisualizationHook in mmseg/engine/hooks/visualization_hook.py: SegVisualizationHook.init() got an unexpected keyword argument 'save_prob'
bash tools/dist_train.sh configs/m2f_psudo/m2f-sl22-bt4-80k-512x-VOC.py 2
bash tools/dist_train.sh configs/m2f_psudo/m2f-sl22-bt4-100k-512x-COCO.py 2
seem to be for Swin-L.
If to train R101, what would be the command for PASCAL VOC2012 and MS COCO2014?
Hi, thank you for the excellent job!
The files in experiments folder are all generated by running the code? Are there some stuff that are prior knowledge to help with the training. I feel confusion about this problem: "FileNotFoundError: [Errno 2] No such file or directory: 'experiment/VOC/cls/infer/final/affx2,at_score,att2affx1/ann,affed/seed/2009_004108.png'". But it didn't generate these files last step.
Thank you for your explain!
Best