MillX's repositories
3d-bat
3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling
AdelaiDet
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
albumentations
fast image augmentation library and easy to use wrapper around other libraries
Awesome-MXNet
A curated list of MXNet examples, tutorials and blogs.
Awesome-NAS
A curated list of neural architecture search (NAS) resources.
batch-feature-erasing-network
Official source code of Batch Feature Erasing for Person Re-identification and Beyond
CBNet
Composite Backbone Network
chinese_ocr
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
context_aug
Context-driven data augmentation for Object Detection (ECCV'18)
gpt2-ml
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
lift-splat-shoot
Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)
NTIRE2019_EDRN
My solution for NTIRE2019 real super-resolution
nuscenes-devkit
The dev-kit of the nuScenes dataset.
open-images-2019-instance-segmentation
7th place solution to the Open Images 2019 Instance Segmentation competition
pod_compare
Code for our paper titled: "A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving"
pysot
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.
R2CNN_FPN_Tensorflow
R2CNN: Rotational Region CNN Based on FPN (Tensorflow)
reid-strong-baseline
Bag of Tricks and A Strong Baseline for Person Re-identification
reid_baseline
sota of reid model
Semantic-Segmentation-Suite
Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!
SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
TensorRT-CenterNet
tensorrt5 , centernet , centerface, deform conv, int8
TransparentChassisCuda
生成基于cuda的环视拼接透明底盘功能的库，用于泊车感知拼接工程集成
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.