Light-Reflection's repositories
Bottleneck-Transformers-for-Visual-Recognition
PyTorch Implementation of BoTNet. Link to paper: https://arxiv.org/abs/2101.11605
Road-Damage-Detection
Dockerized Flask App to segment cracks and detect potholes on road images.
Automatic-Parking
Automatic parallel parking system including path planning, path tracking, and parallel parking in a designed environment written in python.
avatarify
Avatars for Zoom, Skype and other video-conferencing apps.
aw_nas
aw_nas: A Modularized and Extensible NAS Framework
byteps
A high performance and generic framework for distributed DNN training
CV-Backbones
CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
CycleMLP
[ICLR'22 Oral] Implementation of "CycleMLP: A MLP-like Architecture for Dense Prediction"
d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。英文版即伯克利“深度学习导论”教材。
Distance_measurement_using_single_camera
using single camera to measure the distance opencv python,
Dive-into-DL-PyTorch
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Few_Shot_Distribution_Calibration
[ICLR2021 Oral] Free Lunch for Few-Shot Learning: Distribution Calibration
gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
HR-NAS
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers (CVPR21 Oral)
MULLS
MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Square [ICRA '21]
NAS-with-Proxy-data
Official code of "NAS acceleration via proxy data", IJCAI21
NAS_FPN_Tensorflow
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
NLP_ability
总结梳理自然语言处理工程师(NLP)需要积累的各方面知识，包括面试题，各种基础知识，工程能力等等，提升核心竞争力
nsganetv2
[ECCV2020] NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
once-for-all
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
Parallel-PIGANs
This is the code of parallel PIGANs
PINTO_model_zoo
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. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin]
simpledet
A Simple and Versatile Framework for Object Detection and Instance Recognition
tensorflow-yolov3
🔥 TensorFlow Code for technical report: "YOLOv3: An Incremental Improvement"
uninas
A highly modular PyTorch framework with a focus on Neural Architecture Search (NAS).
Yolo-Fastest
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB