I like ML that runs fast (and sometimes works too).
stable-diffusion-nvidia-docker. GPU-ready Dockerfile to run Stability.AI stable-diffusion model v2 with a simple web interface. Includes multi-GPUs support.
370lane-detection. Implementation of a SegnetConvLSTM for Lane Detection, exploiting spatiotemporal relations in data to detect roadlanes
24image_segmentation. Image Segmentation using k-means, n-cuts and superpixels
11pyramid-cnn-leaves-segmentation. PyTorch implementation of the Pyramid CNN network from "A Pyramid CNN for Dense-Leaves Segmentation"
9continual-habitat-lab. High Level library for running Habitat-Sim for Continual Learning applications.
6avalanche. Avalanche: an End-to-End Library for Continual Learning.
5autograd.rs. Simple Deep Learning library in Rust based on ndarray.
4stable-diffusion-webui. Stable Diffusion web UI
4ai-toy-games. Implementation of toy games and classical AI solvers (+reinforcement learning cameo).
3stable-diffusion-react-ui. React UI for Stable Diffusion
2vllm. A high-throughput and memory-efficient inference and serving engine for LLMs
2doc2vec_tryouts. trying out some doc2vec features with some data-sets
1my-linux-config. My zsh config for getting up to speed in a new server/VM
1