Lucas's repositories
llama.cpp
LLM inference in C/C++
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
daily-paper-pose-estimation
读过的姿态检测论文
YOLOv6
YOLOv6: a single-stage object detection framework dedicated to industrial application.
mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
Python
精通python練習
nanodet
⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
daily-paper-visual-tracking
记录每天整理的视觉目标跟踪论文
awesome-3D-Room-Layout-Estimation
paper list of 3D room layout estimation from panorama or perspective images
CFL
Tensorflow implementation of our end-to-end model to recover 3D layouts. Also with equirectangular convolutions!
mmtracking
OpenMMLab Video Perception Toolbox. It supports Single Object Tracking (SOT), Multiple Object Tracking (MOT), Video Object Detection (VID) with a unified framework.
EfficientNet-PyTorch
A PyTorch implementation of EfficientNet
detr
End-to-End Object Detection with Transformers
AlphaRefine
Official implementation for Alpha-Refine
RLT-DIMP
Robust Long-Term Object Tracking via Improved Discriminative Model Prediction
SiamDW
[CVPR'19 Oral] Deeper and Wider Siamese Networks for Real-Time Visual Tracking
siamban
Siamese Box Adaptive Network for Visual Tracking
benchmark_results
Visual Tracking Paper List
DROL
Discriminative and Robust Online Learning for Siamese Visual Tracking [AAAI2020]
360-Scene-Understanding
Some tools to work with 360 images!
EfficientDet.Pytorch
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
Dense-RepPoints
Dense reppoints: Representing visual objects with dense point sets https://arxiv.org/abs/1912.11473
awesome-segmentation-saliency-dataset
A collection of some datasets for segmentation / saliency detection. Welcome to PR...:smile:
EmbedMask
EmbedMask: Embedding Coupling for One-stage Instance Segmentation
video_analyst
A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.
segment-any-moving
Code for "Towards Segmenting Anything That Moves"
siamese-mask-rcnn
Siamese Mask R-CNN model for one-shot instance segmentation