Ge Zheng's repositories
Deep-Image-Matting
This is tensorflow implementation for paper "Deep Image Matting"
Additive-Margin-Softmax
This is the implementation of paper <Additive Margin Softmax for Face Verification>
Salient-Object-Detection
This is tensorflow implementation for cvpr2017 paper "Deeply Supervised Salient Object Detection with Short Connections"
Udacity-ML-nanodegree
This is the repository which contains all 6 projects' source code in ML nano degree.
detectron2
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
mmdetection
Open MMLab Detection Toolbox with PyTorch
pretrained-models.pytorch
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
aima-pseudocode
Pseudocode descriptions of the algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"
BEVDepth
Official code for BEVDepth.
Celebrity-Face-Dataset-Filter
This code can detect outlier images from a specific celebrity images set.
DAB-DETR
[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
DeFCN
End-to-End Object Detection with Fully Convolutional Network
FateScript.github.io
Feng Wang's blog
GAN-tensorflow
Implement Generative Adversarial Nets by Tensorflow
Joker316701882.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
LeNet
Implement the LeNet using tensorflow to recognize handwritten number. Training with MNIST.
MLND_CN_Capstone
nd009-cn-advanced-capstone，针对Udacity CN MLND 毕业项目
mmcv
Open MMLab Computer Vision Foundation
nanodet
⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Xraft.Image.Base
Image base for blog xraft.github.io
YOLOS
You Only Look at One Sequence (NeurIPS 2021)
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/