SGLang is a high-performance serving framework for large language models and multimodal models.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Serbian LLM Eval.

Inference Llama 2 in one file of pure C

Implementation of the deepmind Flamingo vision-language model, based on Hugging Face language models and ready for training

stable diffusion webui colab

Open Source Graph Neural Net Based Pipeline for Image Matching

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

Finds the minimum bounding box from a point cloud.

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Pytorch implementation of the GradNorm. GradNorm addresses the problem of balancing multiple losses for multi-task learning by learning adjustable weight coefficients.

[CVPR 2020] CenterMask : Real-time Anchor-Free Instance Segmentation

Jekyll Template - Mediumish

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

This is the code for "Unity AI" by Siraj Raval on Youtube

My personal page

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

torch-optimizer -- collection of optimizers for Pytorch

Kaggle RPS Competition 4th Place Solution

Remap, mask, renumber, unique, and in-place transposition of 3D labeled images. Point cloud too.

37th place solution for the 2020-2021 Kaggle competition "Rock, Paper, Scissors"

Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.

Pytorch implementation of Center Loss