KNN lifting (Pointcloud to Graph) with New dataset MNIST

[cshjin]

Main changes:

• implement graph to point cloud lifting
• add point cloud dataset
  • add MNIST dataset (2D point cloud)

With details:

• update readme.md with additional torch_vision package (MNIST dataset)

• update github action test_codebase and test_tutorials with additional torch_vision package

• add mnist_to_pointcloud function in data/utils/utils.py

• update modules/data/load/loaders.py with additional mnist_to_pointcloud function

• update modules/data/utils/custom_dataset with specific repr for different dataset.

• add file configs/dataset/MNIST.yaml for MNIST dataset

• add new plot_point_cloud function in modules/utils/utils.py for visualization

• add file transforms/liftings/pointcloud2graph/knn_lifting.py for KNN lifting

• update TRANSFORMS in modules/transforms/data_transform.py with additional GraphKNNLifting

• add file modules/graph/gcn.py

• add file config/models/gcn.yaml

• add example in tutorial/pointcloud2graph/knn_lifiting.ipynb

Tutorial provided at notebook
from point cloud

to

by KNN lifting.

NOTE:
additional torch_vision package is required to get MNIST dataset.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[gbg141]

Hello @cshjin! Thank you for your submission. As we near the end of the challenge, I am collecting participant info for the purpose of selecting and announcing winners. Please email me (or have one member of your team email me) at [email protected] so I can share access to the voting form. In your email, please include:

• your first and last name (as well as any other team members)
• the title of the method you implemented
• the input domain of the method you implemented
• the output domain of the method you implemented
• your pull request number (KNN lifting (Pointcloud to Graph) with New dataset MNIST #19)

Before July 12, make sure that your submission respects all Submission Requirements laid out on the challenge page. Any submission that fails to meet this criteria will be automatically disqualified.