VoxFormer
Kornia
VoxFormer | Kornia | |
---|---|---|
2 | 11 | |
973 | 9,473 | |
2.4% | 2.6% | |
6.9 | 9.4 | |
6 months ago | 1 day ago | |
Python | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
VoxFormer
-
🎬 A New AI Research Proposes VoxFormer: A Transformer-Based 3D Semantic Scene Completion Framework
Quick Read: https://www.marktechpost.com/2023/03/04/a-new-ai-research-proposes-voxformer-a-transformer-based-3d-semantic-scene-completion-framework/ Paper: https://arxiv.org/pdf/2302.12251.pdf Github: https://github.com/nvlabs/voxformer
- [R] [N] VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion.
Kornia
-
[News] Kornia 0.6.6: ParametrizedLine API, load_image support for Apple Windows Developer, integration demos with Hugging Face and many more.
👉 https://github.com/kornia/kornia/releases/tag/v0.6.6
- [P] Kornia: Differential Computer Vision
- Kornia: Differential Computer Vision
-
Hacker News top posts: May 10, 2022
Kornia: Differential Computer Vision\ (3 comments)
- Preprocessing for NN on GPU
-
Top 5 Python libraries for Computer vision
Kornia - Kornia is a differentiable computer vision library for PyTorch. It consists of a set of routines and differentiable modules to solve generic computer vision problems. At its core, the package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions.
-
[D] CPU choice for machine learning server (Epyc vs. Threadripper)
Between "not being sure yet" about GPU operations in pre-processing and choosing high-end CPUs, I think you are overthinking the wrong alternative. Besides DALI, check whether you are using codecs besides nvidia/torchvision-supported jpeg and png, and if other GPU CV libraries meet your needs: torchvision kornia
-
[P] Using PyTorch + NumPy? A bug that plagues thousands of open-source ML projects.
Use kornia.augmentation where this problem is solved doing the augmentations in batch outside the dataloader. https://github.com/kornia/kornia
What are some alternatives?
fiftyone - The open-source tool for building high-quality datasets and computer vision models
OpenCV - Open Source Computer Vision Library
MonoScene - [CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image
Face Recognition - The world's simplest facial recognition api for Python and the command line
Serpent.AI - Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
PixelLib - Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
SimpleCV - The Open Source Framework for Machine Vision
Autonomous-car - Autonomous car using ESP32.
multi-object-tracker - Multi-object trackers in Python
gaps - A Genetic Algorithm-Based Solver for Jigsaw Puzzles :cyclone:
tesserocr - A Python wrapper for the tesseract-ocr API