bytemaster's starred repositories
Dreambooth-Stable-Diffusion
Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
LLaMA-Adapter
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
GroundingDINO
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
lora-scripts
LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
Torch-Pruning
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
Mask2Former
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
SensorsCalibration
OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving
autodistill
Images to inference with no labeling (use foundation models to train supervised models).
Lidar_AI_Solution
A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).
BEVFormer_tensorrt
BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).
bevdet-tensorrt-cpp
BEVDet implemented by TensorRT, C++; Achieving real-time performance on Orin