alinlab / ifseg Goto Github PK
View Code? Open in Web Editor NEWIFSeg: Image-free Semantic Segmentation via Vision-Language Model (CVPR 2023)
IFSeg: Image-free Semantic Segmentation via Vision-Language Model (CVPR 2023)
Hi,
I allocate 64g REM with 4 A100 GPUs
#SBATCH --time=72:00:00
#SBATCH --mem=64g
#SBATCH --job-name="ifseg"
#SBATCH --partition=gpu
#SBATCH --gres=gpu:a100:4
#SBATCH --cpus-per-task=4
#SBATCH --mail-type=BEGIN,END,ALL
sh run_scripts/IFSeg/coco_unseen.sh
Here is the distributed training error message. Any input? Thanks.
--Ruida
single-machine distributed training is initialized.
/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/site-packages/torch/distributed/launch.py:180: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects --local_rank
argument to be set, please
change it to read from os.environ['LOCAL_RANK']
instead. See
https://pytorch.org/docs/stable/distributed.html#launch-utility for
further instructions
warnings.warn(
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -11) local_rank: 0 (pid: 2012686) of binary: /gpfs/gsfs12/users/me/conda/envs/ifseg/bin/python3
Traceback (most recent call last):
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/site-packages/torch/distributed/launch.py", line 195, in
main()
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/site-packages/torch/distributed/launch.py", line 191, in main
launch(args)
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/site-packages/torch/distributed/launch.py", line 176, in launch
run(args)
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/site-packages/torch/distributed/run.py", line 753, in run
elastic_launch(
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 132, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/gpfs/gsfs12/users/me/conda/envs/ifseg/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 246, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
First of all, thank you for conducting such great research.
Could you give me an example of how to learn and evaluate a new dataset?
Thank you for reading!
Excellent work! Thanks for the release.
I followed the instruction here to perform image-free training on ADE20k val, but got extremely low mIoU results(0.0001). Below is my training log:
Is there any bug or possible wrong step in the training procedure that I performed? Or any hint?
Thanks in advance.
Hi,
coco_fine.sh:
data=${data_dir}/fineseg_refined_val2017.tsv,${data_dir}/fineseg_refined_val2017.tsv
coco_unseen.sh:
data=${data_dir}/unseen_val2017.tsv,${data_dir}/unseen_val2017.tsv
Could you leave me input on why the two valid dataset TSV files were specified in the data variable?
Thanks,
--Ruida
Hi,
Thanks for your excellent work. I am wondering when the code will be released.
Best regards,
Yuhang
Did the backbone been fine-tuned on the COCO dataset before extract the feature for the cropped image?
Thanks for your excellent work. I have downloaded '2017train images', '2017val images', and '2017Stuff Train/val annotations' from the website, and I revised the data path in the python file. But I can't get the correct csv generation, could you give me help?
Hi, thanks for your amazing work. Are there plans to release a HF demo?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.