bearid
courses
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.
bearid
-
Bearcam Companion: GitHub, User Groups and Rekognition
By the end of my previous post, I had reached a good baseline for the Bearcam Companion app. It was past time to start tracking the code in a version control system. Since we already have the BearID Project on GitHub, I decided to use the same for this project.
-
BearCam Companion
We initially focused on building a photo dataset of the bears at Brooks Falls. We collected photos from individuals and a large set from the National Parks Service's bear monitoring program at Katmai. From there we got involved with Dr. Melanie Clapham, a conservation scientist in British Columbia, studying the bears of Glendale Cove. We built a computer to run our ML training and developed an open source application, bearid, which we provided to Melanie as a Docker container she could run in the field on a laptop.
-
AWS Community Builders: My First Step
The BearID Project application bearid runs on a server. It takes photos or videos as inputs and outputs a sequence of boxes labeled with the bear's name. This can only happen after someone goes into the field (or, forest), collects a bunch of SD cards from trail cameras, and uploads them to the server. This happens a few times a year. If the trail camera was connected, it could send data to the cloud, but the connection would probably be expensive. If the camera could detect and identify the bear and send only the metadata to a server, we could update the researcher in real time. I have less experience in this area, so connecting it all together with AWS services will be a real learning experience for me.
courses
-
If you are looking for free courses about AI, LLMs, CV, or NLP, I created the repository with links to resources that I found super high quality and helpful. The link is in the comment.
I found it: https://github.com/SkalskiP/courses
https://github.com/SkalskiP/courses/discussions/20. Wouldhttps://github.com/SkalskiP/courses/discussions/20 that format be helpful?
- Repo con cursos gratis sobre IA (en inglés)
- GitHub - SkalskiP/courses: This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI)
-
Anyone know of any good video lectures for Computer Vision? From great professors at well-regarded universities
This is a popular repo with cv specific resources https://github.com/SkalskiP/courses
- Curated collection of high quality ai resources
-
If you are looking for courses about Artificial Intelligence, I created the repository with links to resources that I found super high quality and helpful. The link is in the comment.
link: https://github.com/SkalskiP/courses
What are some alternatives?
facenet - Face recognition using Tensorflow
DNABERT - DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
deepface - A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
course - The Hugging Face course on Transformers
facetorch - Python library for analysing faces using PyTorch
WhereIsAI - AI company, product, and tool collection.
Face Recognition - The world's simplest facial recognition api for Python and the command line
vectory - Vectory provides a collection of tools to track and compare embedding versions.
SpeciesClassification - To gain access, please finish setting up this repository now at: https://repos.opensource.microsoft.com/microsoft/wizard?existingreponame=SpeciesClassification&existingrepoid=169153301
Mask3D - Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
desktop - Focus on what matters instead of fighting with Git.
wit - WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.