search

skumra / robotic-grasping

Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.
Other
456 stars 119 forks source link

generate_cornell_depth #38

Closed nickhward closed 3 years ago

nickhward commented 3 years ago

When I run the command: python -m utils.dataset_processing.generate_cornell_depth /Cornel_Grasping_dataset/archive

This is was I get:

(venv) nicholasward2@nicholasward2-Alienware-Aurora-R7:~/robotic-grasping$ python -m utils.dataset_processing.generate_cornell_depth /Cornel_Grasping_dataset/archive Matplotlib is building the font cache; this may take a moment.

Then it stops running immediately. Does anyone have any suggestions on how to fix this issue?

nickhward commented 3 years ago

I figured out that I just wasn't writing the path correctly. I just copied the absolute path from properties. Also in case anyone is having issues with finding the Cornell data-set because the link on GitHub repo no longer works you can find it here: https://www.kaggle.com/oneoneliu/cornell-grasp

silver60229 commented 3 years ago

當我運行命令時： python -m utils.dataset_processing.generate_cornell_depth /Cornel_Grasping_dataset/archive

這是我得到的：

(venv) nicholasward2@nicholasward2-Alienware-Aurora-R7:~/robotic-grasping$ python -m utils.dataset_processing.generate_cornell_depth /Cornel_Grasping_dataset/archive Matplotlib 正在構建字體緩存；這可能需要一點時間。

然後就立即停止運行。有沒有人對如何解決問題有任何建議？

Can I ask you for the complete usage method? For example, enter python -m utils.dataset_processing.generate_cornell_depth "path" in the robotic-grasping-master folder in "cmd"? Thank you

nickhward commented 3 years ago

@silver60229 So I extracted the Cornell data set into a folder called Cornell_Grasping_dataset that is located in the main robotic-grasping folder.

Then the whole command in terminal looked as such: cd robotic-grasping

Then: python -m utils.dataset_processing.generate_cornell_depth /home/nicholasward2/robotic-grasping/Cornell_Grasping_dataset/archive

I just made sure that I used an absolute path to my data set and it worked.

Hopefully this answers your question.

zhenjing commented 6 months ago

copy ./utils/dataset_processing/generate_cornell_depth.py ./

modify generate_cornell_depth.py: pcds = glob.glob(os.path.join(args.path, '', 'pcd[0-9].txt')) => pcds = glob.glob(os.path.join(args.path, 'pcd*[0-9].txt'))

other way: recursive search all subdir pcds = glob.glob(os.path.join(args.path, '*', 'pcd[0-9].txt'), recursive=True)