youhuang67 / interformer Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
In Table 2 of the paper, you adopt different image sizes for different methods (with 512 for InterFormer). Would it be unfair for the performance (NoC) comparison?
Hello author, thank you very much for your outstanding contribution.
In Evaluation,To evaluate on SBD with InterFormer-Tiny, run: CUDA_VISIBLE_DEVICES=0,1,2,3 bash tools/dist_clicktest.sh work_dirs/interformer_tiny_coco_lvis_320k/iter_320000.pth 4 --dataset sbd --size_divisor 32.
I encountered an error while running:Traceback (most recent call last):
File "/home/student1/wbj/InterFormer/tools/clicktest.py", line 316, in
main()
File "/home/student1/wbj/InterFormer/tools/clicktest.py", line 219, in main
dataset = build_dataset(cfg.data.test)
File "/home/student1/anaconda3/envs/py38_wbj/lib/python3.8/site-packages/mmcv/utils/config.py", line 50, in getattr
raise ex
AttributeError: 'ConfigDict' object has no attribute 'test'
How should I solve it?
The full output of the error:
(py38_wbj) student1@user-PowerEdge-R555:~$ CUDA_VISIBLE_DEVICES=0,1 bash /home/student1/wbj/InterFormer/tools/dist_clicktest.sh "/home/student1/wbj/InterFormer/work_dirs/interformer_tiny_coco_lvis_320k/iter_320000.pth" 2 --dataset berkeley --size_divisor 32
/home/student1/anaconda3/envs/py38_wbj/lib/python3.8/site-packages/torch/distributed/launch.py:178: 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(
WARNING:torch.distributed.run:
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
None
32 2023-07-05 01:55:19,482 - mmseg - INFO - OMP num threads is 1 2023-07-05 01:55:20,168 - mmseg - INFO - Multi-processing start method is
None2023-07-05 01:55:20,169 - mmseg - INFO - OpenCV num_threads is
32
In SimpleClick, each image undergoes 1 to 3 iterations. During the iteration for one image, previous outputs and new coordinate features are processed through the entire model each time. In your architecture, previous outputs and new coordinate features are fed into 'Feature Decoding.' Therefore, I believe that during the iteration for one image, the image features from 'Feature Encoding' are reused.
Is my understanding correct?
I'm sorry to bother you again. I have been tracing your code, but I still cannot find the training code that consists of the complete training flow. Could you give me a hint?
Hello, I run the demo.py with 'python demo.py weights/iter_320000.pth --device cuda:0' successfully. My gpu is RTX 4090 D with 24GB memory. When I opened a 960 × 1440 image, it took up more than 24GB and I got a "CUDA out of memory" error. Even when I opened a 110 × 118 image, it took up 3GB of memory. Why is that?
"The trained weights are available at [InterFormer(https://drive.google.com/drive/folders/1kEll7pqulpE00JcCvSut0e9C4peKDWRe?usp=sharing)" in READE.ME is broken.
Would you be able to add a license to your code?
Dear authors, @YouHuang67
Thanks for releasing the code and models. I am trying to rerun your released light model on DAVIS, but the numbers look better than you reported in the paper. For example, I got 5.54 for NoC90, but you reported 6.19. Also, your code will crash for case 008.jpg, so I need to remove it for evaluation. Missing one case won't cause such a big difference, so I may need your help to figure out the issue.
BTW, the results for Berkeley are the same. I look forward to hearing from you! Thanks in advance.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.