Coder Social home page Coder Social logo

hal-42 / fma-wsss Goto Github PK

View Code? Open in Web Editor NEW
33.0 33.0 4.0 8.98 MB

This repo is a implementation of the Foundation Model Assisted Weakly Supervised Semantic Segmentation. The code is developed based on the Pytorch framework.

License: Apache License 2.0

Python 99.81% Jupyter Notebook 0.19%

fma-wsss's People

Contributors

hal-42 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

fma-wsss's Issues

<class 'utils.cache_dir.CacheDir'>: CacheDir状态为未启用,terminate无效。`.

Hi!

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。.

Do you have any insight? Thank you!

Generate SAM-based quasi-superpixel步骤出现问题

你好,在这一步中
python src/tasks/sam_auto_seg/par_run.py --purge 1 -b 256 -w 50 -m uncompressed_rle -c configs/VOC/sams/cfg.py

我是运行下面的
CUDA_VISABLE_DEVICES=1,2 python src/tasks/sam_auto_seg/par_run.py --purge 1 -m uncompressed_rle -c configs/VOC/sams/cfg.py
然后出现了这样的警告,一直循环出现
图片1
请问是什么问题,该怎么解决啊

No such file or directory

你好,当我运行到这一步的时候,

Train classification task.

python src/tasks/train_coop/run.py -i 0 -e 0 -c configs/VOC/seg/cfg.py
出现下面这个
图片1
FileNotFoundError: [Errno 2] No such file or directory: 'experiment/VOC/cls/infer/final/affx2,at_score,att2affx1/ann,affed/seed/2009_004108.png'
请问这些图片是怎么来的,是第一步
python src/tasks/sam_auto_seg/par_run.py --purge 1 -b 256 -w 50 -m uncompressed_rle -c configs/VOC/sams/cfg.py
生成的吗,但我是按步骤来的,并没有这些图片啊

seg_cls_labels.pkl文件没有

你好,
图片1
可以提供下seg_cls_labels.pkl文件吗,数据集太大了,还没下载,这是用我已有的数据集跑的,但缺少这个文件

Could you upload the files to Onedrive or Google drive.

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?

Multi-label contrastive loss implementation

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.

SegVisualizationHook.__init__() got an unexpected keyword argument 'save_prob'

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'

Custom Dataset

Does this code work for other datasets? If yes, what should be changed for the code to work?

Usage

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?

The files in experiments folder are all generated by running the code?

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

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.