Sebastian Cavada's Projects
Computer Vision project for detecting cars at intersections
Winner solution for the Pioneers4.0 Hackathon 2024
This is a template project to help launch a project that is ready for VR/AR development right out of the box.
š„ The fastest and powerful Python library for Instagram Private API 2022
Load, pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.
LLM Workshop by Sourab Mangrulkar
pip package to train and evaluate phinet on multimedia analytics.
The Mojo Programming Language
A component to integrate into your website nano payments
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Few-Shot Video Object Recognition with Embedding Adaptation and Uniform Clip Sampling: Winner of ORBIT Few-Shot Object Recognition Challenge 2022
The ORBIT dataset is a collection of videos of objects in clean and cluttered scenes recorded by people who are blind/low-vision on a mobile phone. The dataset is presented with a teachable object recognition benchmark task which aims to drive few-shot learning on challenging real-world data.
I am a pragmatic and creative person with a passion for new technologies, particularly in the fields of artificial intelligence and computer vision. Visit my website :)
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
An unofficial implementation of paper 3D Gaussian Splatting for Real-Time Radiance Field Rendering by taichi lang.
NEW - YOLOv8 š in PyTorch > ONNX > CoreML > TFLite
The repository of my thesis, and the implementation of the codebase for the research