-
Notifications
You must be signed in to change notification settings - Fork 2
torchvision in R improvements
Toby Dylan Hocking edited this page Oct 18, 2024
·
2 revisions
torch is a popular package for machine learning, and specifically torchvision provides direct access to computer-vision models and datasets, but R support is missing some features compared to python.
keras/tensorflow in R interface with python, and so are even more difficult to install, compared to torch (uses C/C++ code).
- Implement all of the torchvision data sets: https://github.com/mlverse/torchvision/issues/104
- Implement torchvision models covering 5 new computer-vision tasks:
- Object Detection model like FasterRCNN : https://github.com/mlverse/torchvision/issues/54#issuecomment-885201975 and SSD
- Instance Segmentation model like Mask R-CNN
- Keypoint Detection model like Keypoint R-CNN
- Semantic segmentation model like FCN
- Quantized models providing low footprint image embedding like Quantized ResNet
Torch and torchvision are extremely popular so this project could have a large impact.
Contributors, please contact mentors below after completing at least one of the tests below.
- EVALUATING MENTOR: Christophe Regouby [email protected] is the maintainer of one of the packages in the torch ecosystem, and contributor to many R packages.
- Toby Hocking [email protected] is the author of numerous R packages, and has been mentor/admin for R-GSOC since 2013.
Contributors, please do one or more of the following tests before contacting the mentors above.
- Easy: install torch, follow instructions in one of the vignettes to make a figure using Rmd, show us your Rmd source and output HTML/PDF.
- Medium: adapt the Loading data vignette to the case of the spam data.
- Hard: fork torch and write a PR that adds your data loader for the spam data, along with tests and documentation.
Contributors, please post a link to your test results here.
- EXAMPLE CONTRIBUTOR 1 NAME, LINK TO GITHUB PROFILE, LINK TO TEST RESULTS.