Coder Social home page Coder Social logo

Comments (10)

Steve-Tod avatar Steve-Tod commented on May 28, 2024

Those codes are quite messy now. If you need them, I'll release the code for data generation once I get a chance to clean it up.

from ditto.

buptmengjj avatar buptmengjj commented on May 28, 2024

Those codes are quite messy now. If you need them, I'll release the code for data generation once I get a chance to clean it up.

Yes, I need. I would be very grateful if you could release them!

from ditto.

Steve-Tod avatar Steve-Tod commented on May 28, 2024

I see, I'll work on it when I have time.

from ditto.

buptmengjj avatar buptmengjj commented on May 28, 2024

Hello, we want to make a dataset and input it into your network for experiment. Before you publish the data pre-processing process, I learned about the content of shape2motion dataset. In the process, I have some problems and hope to get your help. Firstly, I use np.shape() outputs the dimension of data ["start_occ_list"], and the result is (n, 100000). I think n represents the number of parts of the object, but what does the data 1000000 represent? Secondly, what is the content of data[start_p_occ]? Thank you very much for your help!

from ditto.

Steve-Tod avatar Steve-Tod commented on May 28, 2024

That's the number of occupancy point samples. "start_p_occ" is the query points for occupancy at the start frame (before interaction). "start_occ_list" is the corresponding list of occupancy results for each part.

from ditto.

buptmengjj avatar buptmengjj commented on May 28, 2024

Hi! I really appreciate your patience in answering my questions. I learned from the paper—— "the ground_truth occupancy is queried from the ground truth mesh", but I'm wondering how did you get the ground truth mesh of the object before and after the interaction?

from ditto.

Steve-Tod avatar Steve-Tod commented on May 28, 2024

Hi, we get ground truth through API in Pybullet, like here.

from ditto.

buptmengjj avatar buptmengjj commented on May 28, 2024

Hi, are the pc_seg_start and pc_seg_end also queried from mesh? Can you share the code about segmentation? In addition, how to get the screw_axis and the screw_moment? Thank you very much, you really helped me a lot!

from ditto.

Steve-Tod avatar Steve-Tod commented on May 28, 2024

Hi there, I finished cleaning up the data generation code and released it here. You can refer to the code here for more details.

pc_seg_start and pc_seg_end were not used in Ditto. screw_axis and screw_moment are from Pybullet.

from ditto.

buptmengjj avatar buptmengjj commented on May 28, 2024

Hi there, I finished cleaning up the data generation code and released it here. You can refer to the code here for more details.

pc_seg_start and pc_seg_end were not used in Ditto. screw_axis and screw_moment are from Pybullet.

Your release is very timely. Thank you very much!

from ditto.

Related Issues (12)

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.