aww1q's repositories
aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
AwesomeCpp
---AWESOME--- C++学习笔记和常见面试知识点,C++11特性,包括智能指针、四种强制转换、function和bind、移动语义、完美转发、tuple、多态原理、虚表、友元函数、符号重载、函数指针、深浅拷贝、struct内存对齐、volatile以及union\static等各种关键字的用法等等,还新添了其他算法和计算机基础的难点,力求简洁清晰
BaiduImageSpider
一个超级轻量的百度图片爬虫
deepgaze
Computer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.
FaceDetection
:star2: Human Face Detection based on AdaBoost
Halpe-FullBody
Halpe: full body human pose estimation and human-object interaction detection dataset
headpose_final
Human head pose estimation using Keras over TensorFlow.
KD_methods_with_TF
Knowledge distillation methods implemented with Tensorflow (now there are 11 (+1) methods, and will be added more.)
laeonetplus
LAEO-Net++
mediapipe-bin
MediaPipe Python Wheel installer for RaspberryPi OS aarch64, Ubuntu aarch64, Debian aarch64 and Jetson Nano.
mediapipe-python-sample
MediaPipeのPythonパッケージのサンプルです。2021/07/23時点でPython実装のある7機能(Hands、Pose、Face Mesh、Holistic、Face Detection、Objectron、Selfie Segmentation)について用意しています。
Minimal-Hand-pytorch
PyTorch reimplementation of minimal-hand (CVPR2020)
MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
nanodet
⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
open_model_zoo
Pre-trained Deep Learning models and demos (high quality and extremely fast)
second.pytorch
PointPillars for KITTI object detection
sense
Enhance your application with the ability to see and interact with humans using any RGB camera.
sklearn-classification
Data Science Notebook on a Classification Task, using sklearn and Tensorflow.
tensorflow-yolov3
🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"
tfjs-models
Pretrained models for TensorFlow.js
Yolo-FastestV2
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/