XiaoJiNu's repositories
deep-head-pose
:fire::fire: Deep Learning Head Pose Estimation using PyTorch.
3DDFA
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.
AE-WTN
Scaling Object Detection by Transferring Classification Weights
algo
数据结构和算法必知必会的50个代码实现
CenterNet-1
Object detection, 3D detection, and pose estimation using center point detection:
CHINESE-OCR
[python3.6] 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
ChineseBQB
🇨🇳Chinese sticker pack,More joy / Github最有毒的仓库, **表情包大集合, 聚欢乐~
cocoapi
COCO API - Dataset @ http://cocodataset.org/
darknet
Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)
DEye
Keep an Eye on Defects Inspection.
dlib
A toolkit for making real world machine learning and data analysis applications in C++
EfficientNet-PyTorch
A PyTorch implementation of EfficientNet
GazeFollowing
Code for ACCV2018 paper 'Believe It or Not, We Know What You Are Looking at!'
labelme
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
leetcode
LeetCode Solutions: A Record of My Problem Solving Journey.( leetcode题解,记录自己的leetcode解题之路。)
mediapipe
MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines
PADet
object-detection
ScreenToGif
🎬 ScreenToGif allows you to record a selected area of your screen, edit and save it as a gif or video.
siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
SlimYOLOv3
This page is for the SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications
smplify-x
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
styleguide
Style guides for Google-originated open-source projects
tfboys
TensorFlow and Pytorch practice codes with purity and simplicity.
tpu
Reference models and tools for Cloud TPUs.
YOLOv3-model-pruning
对 YOLOv3 做模型剪枝(network slimming),对于 oxford hand 数据集(因项目需要),模型剪枝后的参数量减少 80%,Infer 的速度达到原来 2 倍,mAP 基本不变