catalyst

Catalyst is a PyTorch-based roof for deep learning research and development processes. It focuses on reproducible, rapid experimentation, and codebase reuse. It allows users to create new models instead of writing standard training cycles.

CA

catalyst-team · Image & Photo Processing

STARS3.4K
FORKS396
COMMITS0
CONTRIBUTORS0
VERSIONv22.04
UPDATED3 mo ago
PythonPyTorchDeep LearningMachine LearningApache-2.0

Common commercial products in this category: Adobe Photoshop, Adobe Lightroom, Cloudinary

What can it do?
  • You train and verify PyTorch-based models.
  • On top of the models, you perform final processing steps such as tracking, quantization, pruning and transferring to the ONNX format.
  • By taking back metrics such as accuracy, precision, and recall, you do model evaluation.
User reviews
  • • NeutralHacker News

    Catalyst – Tailwind CSS Application UI Kit

    “It’s not incomplete though. It has all the components you need to fully build a full-featured functioning web application fast. I’ve shipped products with this kit without having to change much code because it’s very well-made. Don’t take it from me - take it from the tens of…”

  • ↑ PositiveHacker News

    Catalyst – Tailwind CSS Application UI Kit

    “Yeah. I’m also not using React. Vue would be nice and so would Phoenix. I think they might add Vue support, as they do for headless-ui. Phoenix is less likely imo. The paid nature makes it hard for the community to fill in that gap, which is a shame. I’d love to collaborate on a…”

My note

Alternative pages

More in: Image & Photo Processing