搜索了下github,把觉得几个不错的深度学习代码整理下列出来,未来可能会去涉及这些。包括人体姿态、物体姿态、人脸相关、行人重识别、行人属性、风格迁移、目标检测。主要以pytorch或tensorflow为主。
目录
人体姿态估计
- Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
- pytorch_Realtime_Multi-Person_Pose_Estimation
- Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)
- Light-weight Single Person Pose Estimator
物体姿态估计
- This research project implements a real-time object detection and pose estimation method as described in the paper, Tekin et al. "Real-Time Seamless Single Shot 6D Object Pose Prediction", CVPR 2018.
人脸、其他
- 一款入门级的人脸、视频、文字检测以及识别的项目.
- papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face Deblurring; Face Generation && Face Synthesis; Face Transfer; Face Anti-Spoofing; Face Retrieval
- A MNIST-like fashion product database. Benchmark
- The world's simplest facial recognition api for Python and the command line
- Face recognition using Tensorflow
- The world's simplest facial recognition api for Python and the command line
行人重识别
- Torchreid: Deep learning person re-identification in PyTorch.
- A tiny, friendly, strong pytorch implement of person re-identification baseline.
- Bag of Tricks and A Strong Baseline for Deep Person Re-identification
- MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
行人属性
- A simple baseline implemented in PyTorch for pedestrian attribute recognition task, evaluating on Market-1501 and DukeMTMC-reID dataset.
- The paper list of person attribute recognition
风格迁移
- Neural style in TensorFlow!
- Neural Style and MSG-Net
目标检测
- Faster R-CNN
- YoloV3 YOLOv3 in PyTorch > ONNX > CoreML > iOS
- YOLOv3
- SSD
OCR
-
yolo3+ocr
- 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
-
Official implementation of Character Region Awareness for Text Detection (CRAFT)
- DataFountain HUAWEI OCR 2019 rank Top1% ,Text Localization using pixellink,Word Recognition using densenet