Xiangrong Chen's Projects
Auto-labelimg based on YOLOv5-5.0 & YOLOv5-Lite
Containing dozens of real-world and synthetic tests, CoreMarkยฎ-PRO (2015) is an industry-standard benchmark that measures the multi-processor performance of central processing units (CPU) and embedded microcrontrollers (MCU)
KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
NCNN+Int8+YOLOv4 quantitative modeling and real-time inference
onnx+onnxruntime+scrfd+flask+web
Detailed comments for ORB-SLAM3
๐๐๐ YOLOSeries of PaddleDetection implementation, PPYOLOE, YOLOX, YOLOv7, YOLOv5, MT-YOLOv6 and so on. ๐๐๐
An effective and flexible tool for data annotation
Parking slot dataset for different scenes
A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]
This is a project based on retinaface face detection, including ghostnet and mobilenetv3
Segment Anything Labelling Tool
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Small object detection: modify yolo.py to add decoupled head of YoloX to Yolov5 and custom TTA, dataset.py to heavily rotatedMosaic w/o artifact or tiny bounding boxes, augmentations.py too add Albumentations transforms.
Push-pull streaming and Web display of YOLO series
YOLOv5 ๐ in PyTorch > ONNX > CoreML > TFLite
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931)
๐
๐
๐
YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
ไฝฟ็จONNXRuntime้จ็ฝฒyolov5-lite็ฎๆ ๆฃๆต๏ผๅ
ๅซC++ๅPythonไธคไธช็ๆฌ็็จๅบ
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors