Giter VIP home page Giter VIP logo

contactdb_prediction's People

Contributors

samarth-robo 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  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

contactdb_prediction's Issues

ConnectionRefusedError: [Errno 111] Connection refused

Hi, I try to train the model by using the bash as follow:
python train_val.py
--data_dir /scratch/grasp_data/meshes_data
--instruction handoff
--checkpoint_dir checkpoints
--config_file configs/pointnet.ini
--device_id 0,1,2,3
While I meet the error about the connection resufed, I have no idea. Did I miss something? I have no idea, could you help me?
The error report is shown:
urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /env/main (Caused by NewConnectionError('<u
rllib3.connection.HTTPConnection object at 0x7f574e887fd0>: Failed to establish a new connection: [Errno 111] Connection refused',))

Computation requirements?

Hello!
I think your work is very interesting. The paper is well written too!
However, the paper does not have details regarding the CPU, GPU and memory requirements for training the models.
Could you expand on that briefly or point me to the details if I missed it by any chance?
(Judging by the size of the batch and code, do you use a Titan X? How much memory does the batch exactly consume?)
Thank in advance. :)

How to preprocess the data

Hi,

thanks for your interesting work. I have a question about how to get the preprocessed data, as you provided in the link, Is there any kinds of scripts for doing this ? Especially about how to transform an arbitrary mesh model to the voxel input ? thanks.

Format of the dataset

Thank you for publishing your fantastic work!

I have a question about the dataset, from the code, I know that there are 7 dimensions of data in a specific .npz file, and the last 4 dimensions are the texture (color of the points?), x-coordinate, y-coordinate, and z-coordinate of the point cloud. I was wondering what are the first 3 dimensions. And how did you obtain the values of the textures?

Thank you again.

Error: Expected object of type torch.cuda.LongTensor but found type torch.cuda.IntTensor for argument #2 'other'

Hi,

Thanks for your interesting work.
When I tried to run:
python eval.py --instruction use --config configs/voxnet.ini --checkpoint data/checkpoints/use_voxnet_diversenet_release/checkpoint_model_86_val_loss=0.01107167.pth --show_object mug
I got one error message. Please check the image below.

image

I have installed all the virtual environment in the environment.yml. I am running in Windows 8.1 with conda 4.8.3.
Also, attaching all the libraries in the txt file below.
tmp.txt

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.