This is an arranged list of repositories about machine learning, computer vision et. al.
1. Computer Vision
1.1. Classification
1.2. Attribute
- SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation. IJCAI2018
- baidu-salers-logo-prediction: (gluon)
1.3. Detection
- awesome-object-detection
- Object detection
- Detectron: FAIR’s research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.(caffe2)
- Deformable-ConvNets
1.3.1. MTCNN
- MTCNN_face_detection_alignment: only inference. (MATLAB)
1.3.2. YOLO
- mxnet-yolo2
- yolo2-pytorch
- pytorch-yolo3
- PyTorch-YOLOv3
- pytorch-yolo-v3: A PyTorch implementation of the YOLO v3 object detection algorithm. (without training files)
- keras-yolo3: Training and Detecting Objects with YOLO3
1.3.3. SSD
- mxnet-ssd: MXNet port of SSD: Single Shot MultiBox Object Detector. Reimplementation of https://github.com/weiliu89/caffe/tree/ssd
1.3.4. Faster RCNN
1.3.5. others
- mx-maskrcnn, TuSimple (MXNet)
1.4. Verification & Recognition
- insightface: Face Recognition Project. (MXNet)
- sphereface: (A-Softmax) SphereFace: Deep Hypersphere Embedding for Face Recognition, CVPR2017. (Caffe)
- facenet: Face Recognition (Tensorflow)
- mx-lsoftmax: (L-Softmax) mxnet version of Large-Margin Softmax Loss for Convolutional Neural Networks.(MXNet)
- NormFace: NormFace: L2 HyperSphere Embedding for Face Verification, Mainly on theory analysis about feature and weights normalization. (Caffe)
- AMSoftmax: upgrades version of NormFace. (Caffe)
1.5. Person ReID
- deep-person-reid (Pytorch)
- Person_reID_baseline_pytorch: (Person_reID_baseline_pytorch): (Pytorch)
- person-re-ranking: Person Re-ranking, CVPR 2017.(caffe)
- AlignedReID-Re-Production-Pytorch
- open-reid: Open source person re-identification library in python https://cysu.github.io/open-reid/ (pytorch)
1.6. Interest Project
- OpenPose: Real-time multi-person keypoint detection library for body, face, and hands estimation.(caffe)
- AlphaPose: Real-Time Multi-Person Pose Estimation System. (pytorch)
- DensePose:A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body.(caffe2)
2. Deep learning
2.1. networks
- diracnets: Training Very Deep Neural Networks Without Skip-Connections (pytorch)
- caffe-DeepRegressionForests: Deep Regression Forests for Age Estimation, CVPR2018.(caffe)
- STN_gluon
2.2. tricks
- Group Normalization: Group Normalization on the task of image classification.(tensorflow)
2.3. theory
- neural-networks-and-deep-learning: Code samples for book “Neural Networks and Deep Learning”.
3. Dataset
- MeGlass: A eyeglass face dataset collected and cleaned for face recognition evaluation.
- Market-1501_Attribute: 27 hand-annotated attributes of Market-1501, for person re-id.
4. Documents
- Transfer Learning: Everything about Transfer Learning and Domain Adaptation. http://transferlearning.xyz/
- deeplearningbook-chinese Deep Learning Book Chinese Translation