v5peng Goto Github PK

balancedgroupsoftmax

CVPR 2020 oral paper: Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax.

caffe-model-zoo

caffe pretrained models and prototxt

crnn_word_captcha

验证码之旋转印刷文字识别实战 项目完全试用Geetest的文字点选项目

ctpn

Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)

g7_capchta_cnn

利用卷积神经网络（CNN）解决图片验证码登录问题。从验证码下载、标注、图片简单处理、神经网络构建到自动化批量标注、人工校验、模型迭代，准确率96%。最后模型应用于自动登录网站爬取数据

gluon-cv

Gluon CV Toolkit

mobilenet-ssd

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

mobilenet-ssd-snpe

mobilenet-ssd snpe demo

paddledetection

Object detection and instance segmentation toolkit based on PaddlePaddle.

paddlex

PaddlePaddle End-to-End Development Toolkit（『飞桨』深度学习全流程开发工具）

pytorch-yolov4

PyTorch ,ONNX and TensorRT implementation of YOLOv4

residual-attention-network

Residual Attention Network for Image Classification

rknn_tutorial

Tutorial includes rknn-envirment building, updating, model transfer, end-to-end YOLO3/self define model training &use, etc.

segment-this-sky

small computer vision draft for sky segmentation. uses opencv and python

snpe-detector-demo-app

yolov3

在pytorch-yolov3的基础上加入了DropBlock和Label Smoothing，Gridmask和mosaic数据增强等进行口罩检测

yolov3-1

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

yolov5

YOLOv5 in PyTorch > ONNX > CoreML > TFLite