concrete-ml
co-tracker
| concrete-ml | co-tracker | |
|---|---|---|
| 8 | 6 | |
| 786 | 2,424 | |
| 6.1% | 4.0% | |
| 9.7 | 6.9 | |
| 2 days ago | 10 days ago | |
| Python | Jupyter Notebook | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
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.
concrete-ml
- Show HN: Logistic Regression Training on Encrypted Data with FHE
- Training ML Models on Encrypted Data with Homomorphic Encryption (FHE)
- FLaNK Stack Weekly 5 September 2023
-
Concrete: A fully homomorphic encryption compiler
If you just want to dive right in, this example from Concrete ML's repository is very clear:
https://github.com/zama-ai/concrete-ml#a-simple-concrete-ml-...
-
Instead of banning ChatGPT for its potential data theft, why don't we use advanced encryption techniques (for example, Homomorphic encryption) to secure our data?
As for ease of use, you should take a look at Concrete. It turns high level python code into FHE equivalents without developers having to know cryptography: https://github.com/zama-ai/concrete-ml
- Concrete ML: transform machine learning models into a homomorphic equivalent
-
Zama Open-Sources Concrete ML v0.2 To Support Data Scientists Without Any Prior Cryptography Knowledge To Automatically Turn Classical Machine Learning (ML) Models Into Their FHE Equivalent
Github: https://github.com/zama-ai/concrete-ml
-
[P] XGboost, sklearn and others running over encrypted data
Hello everyone! Following this post [numpy over encrypted numpy in fhe we are releasing a new lib that allows popular machine learning frameworks to run over encrypted data: https://github.com/zama-ai/concrete-ml
co-tracker
- What things are happening in ML that we can't hear oer the din of LLMs?
-
ML Engineering Online Book
Yes, I think this is very tractable for a first project. I've played around with using AI to do optical-only with pose detection models -- if I had to do it again, I would probably start with this model and try to get it running locally:
https://github.com/facebookresearch/co-tracker
This sounds like a perfect place for you to get started!
- FLaNK Stack Weekly 5 September 2023
-
CoTracker: A Revolutionary 2D Point Video Tracker
(arXiv) (GitHub)
-
Meta AI releases CoTracker, a model for tracking any points (pixels) on a video
LICENSE
Attribution-NonCommercial 4.0 International
https://github.com/facebookresearch/co-tracker/blob/main/LIC...
What are some alternatives?
concrete-numpy - Concrete-Numpy: A library to turn programs into their homomorphic equivalent.
tapnet - Tracking Any Point (TAP)
yolov7-object-tracking - YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking
paxml - Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.
puck - The visual editor for React
FLaNK-HuggingFace-BLOOM-LLM - https://huggingface.co/bigscience/bloom into NiFi
concrete - Concrete: TFHE Compiler that converts python programs into FHE equivalent
openaidemo - Demo of how access the OpenAI API using Java 17
privaxy - Privaxy is the next generation tracker and advertisement blocker. It blocks ads and trackers by MITMing HTTP(s) traffic.
morphir - A universal language for business and technology