Rhys Williams's repositories
vision-at-a-clip
Low-latency ONNX and TensorRT image segmentation with contrastive language-image pre-training based prompts
accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
clip-as-service
🏄 Embed/reason/rank images and sentences with CLIP models
ollama-voice-jetson
Jetson (Xavier series) compatible LLM based assistant and robot control system
whisper-onnx-python
A low-footprint GPU accelerated Speech to Text Python package for the Jetpack 5 era bolstered by an optimized graph
accelerated-vector
A one-stop shop for optimised supplementary or outsourced inference for a wire-pod based Vector robot companion. With Jetson and other SBCs in mind for a local ML hub -
bootFromExternalStorage
Shell scripts to setup a NVIDIA Jetson AGX Xavier, Xavier NX, AGX Orin, or Orin Nano Developer Kit to boot from external storage.
chainlit
Build Conversational AI in minutes ⚡️
CLIP-SAM
Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.
CLIP_Surgery
CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks
detection-datasets
Easily load and transform datasets for object detection
faster-than-requests
Faster requests on Python 3
fastRAG
Efficient Retrieval Augmentation and Generation Framework
jetson_ros2_humble_zed_wrapper
Jetson Nano ROS2 Humble with ZED SDK and ZED ROS2 Wrapper
milvus
Vector database for scalable similarity search and AI applications.
milvus-operator
milvus-operator
mlsd_pytorch
Pytorch implementation of "M-LSD: Towards Light-weight and Real-time Line Segment Detection"
MobileSAM
This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!
ollama-voice-mac
Mac compatible Ollama Voice
rtabmap_drone_example
Example of using move_base with mavros/px4 and rtabmap visual SLAM
Segment-Anything-CLIP
Connecting segment-anything's output masks with the CLIP model; Awesome-Segment-Anything-Works
serve
Serve, optimize and scale PyTorch models in production
siglip-search
A companion project to sam-a-clip - low-latency, accelerated multi-modal vector search
whisper-onnx-tensorrt
ONNX and TensorRT implementation of Whisper
wire-pod
Free, fully-featured server software for the Anki Vector robot.
wirepod-vector-python-sdk
Patched version of a patched version of Cyb3rdog's Vector SDK v0.7.2-dev6 for Python 3.11.0, designed to work with wirepod