chengxi's repositories
CV_Interview
I hope this repo can help you a lot!
2021_algorithm_intern_information
2021年的算法实习岗位/校招公司信息表，和常见深度学习基础、计算机视觉知识笔记、算法岗面试题答案，及暑期计算机视觉实习面经和总结。
Awesome-DeepLearning-Tutorials
Links to useful online tutorials etc. about deep learning
camodocal
CamOdoCal: Automatic Intrinsic and Extrinsic Calibration of a Rig with Multiple Generic Cameras and Odometry
computer-vision-in-action
《计算机视觉实战演练：算法与应用》中文电子书、源码、读者交流社区（更新中，可以先 star）
CV_Notes
「3D视觉(三维重建、SLAM、AR/VR) + 传统图像处理 + 计算机视觉(偏AI) 」重要知识点和面试问题。
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
efficientvit
EfficientViT is a new family of vision models for efficient high-resolution vision.
Face-Detector-1MB-with-landmark
1M人脸检测模型(含关键点)
FaceRecognizer
人脸识别应用
handeye_calib_camodocal
Easy to use and accurate hand eye calibration which has been working reliably for years (2016-present) with kinect, kinectv2, rgbd cameras, optical trackers, and several robots including the ur5 and kuka iiwa.
iAI
保姆级深度学习从入门到放弃，٩◔̯◔۶
imgclsmob
Sandbox for training deep learning networks
lite.ai.toolkit
🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv5. MNN, NCNN, TNN, ONNXRuntime.
micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
MobileSAM
This is the offiicial code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight
ngp_pl
Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)
notes
这个仓库记录自己学习的知识笔记，看过的论文的笔记以及一些其他的知识记录
paper-reading
深度学习经典、新论文逐段精读
ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
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
pytorch_classification
利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码
Pytorch_Retinaface
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
PytorchToCaffe
Pytorch model to caffe model, supported pytorch 0.3, 0.3.1, 0.4, 0.4.1 ,1.0 , 1.0.1 , 1.2 ,1.3 .notice that only pytorch 1.1 have some bugs
SummaryOfLoanSuspension
全国各省市停贷通知汇总
survey-computer-vision-2020
2020-2021年计算机视觉综述论文分方向整理
TNN
TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.
yolov5-comment
yolov5的注释版本