Pinned Repositories
my_orc_keras_verification_code_identification
本项目实现了ocr主流算法gru/lstm+ctc+cnn架构,进行不定长度验证码识别,达到不分割字符而识别验证码内容的效果。验证码内容包含了大小字母以及数字,并增加点、线、颜色、位置、字体等干扰项。本项目对gru +ctc+cnn、lstm+ctc+cnn、cnn三种架构进行了对比,实践说明同等训练下gru/lstm+ctc+cnn架构准确率和速度均明显优于cnn架构,gru +ctc+cnn优于lstm+ctc+cnn,在实验2500个样本数据200轮训练时,gru +ctc+cnn架构在500样本测试准确率达90.2%。本项目技术能够训练长序列的ocr识别,更换数据集和相关调整,即可用于比如身份证号码、车牌、手机号、邮编等识别任务,也可用于汉字识别。
12306
12306智能刷票,订票
AdvancedEAST
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.
age-gender-estimation
Keras implementation of a CNN network for age and gender estimation
chinese_ocr
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
crnn.pytorch
Convolutional recurrent network in pytorch
deep_sort
Simple Online Realtime Tracking with a Deep Association Metric
EAST
A tensorflow implementation of EAST text detector
helloworld
a simple code named helloworld
helmet_dec
GreenVegetables123's Repositories
GreenVegetables123/PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
GreenVegetables123/12306
12306智能刷票,订票
GreenVegetables123/Safety-Helmet-Wearing-Dataset
Safety helmet wearing detect dataset, with pretrained model
GreenVegetables123/Stronger-yolo-pytorch
Pytorch implementation of Stronger-Yolo with channel-pruning.
GreenVegetables123/tensorflow-yolov3
🔥 pure tensorflow Implement of YOLOv3 with support to train your own dataset
GreenVegetables123/yolact
A simple, fully convolutional model for real-time instance segmentation.
GreenVegetables123/recommenders
Best Practices on Recommendation Systems
GreenVegetables123/mAP
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
GreenVegetables123/insightface
Face Analysis Project on MXNet
GreenVegetables123/age-gender-estimation
Keras implementation of a CNN network for age and gender estimation
GreenVegetables123/transferlearning
Everything about Transfer Learning and Domain Adaptation--迁移学习
GreenVegetables123/text-detection-ctpn
text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network
GreenVegetables123/EAST
A tensorflow implementation of EAST text detector
GreenVegetables123/HyperVID
开源移动端车型识别 Mobile Plateform Vehicle Identification Model
GreenVegetables123/deep_sort
Simple Online Realtime Tracking with a Deep Association Metric
GreenVegetables123/keras-arcface
Keras implementation of ArcFace, CosFace, and SphereFace
GreenVegetables123/Stronger-yolo
Improve yolo with latest paper
GreenVegetables123/crnn.pytorch
Convolutional recurrent network in pytorch
GreenVegetables123/tensorflow_models_learning
tensorflow GoogleNet inception V1 V2 V3 V4
GreenVegetables123/my_orc_keras_verification_code_identification
本项目实现了ocr主流算法gru/lstm+ctc+cnn架构,进行不定长度验证码识别,达到不分割字符而识别验证码内容的效果。验证码内容包含了大小字母以及数字,并增加点、线、颜色、位置、字体等干扰项。本项目对gru +ctc+cnn、lstm+ctc+cnn、cnn三种架构进行了对比,实践说明同等训练下gru/lstm+ctc+cnn架构准确率和速度均明显优于cnn架构,gru +ctc+cnn优于lstm+ctc+cnn,在实验2500个样本数据200轮训练时,gru +ctc+cnn架构在500样本测试准确率达90.2%。本项目技术能够训练长序列的ocr识别,更换数据集和相关调整,即可用于比如身份证号码、车牌、手机号、邮编等识别任务,也可用于汉字识别。
GreenVegetables123/helmet_dec
GreenVegetables123/AdvancedEAST
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.
GreenVegetables123/keras-yolov3-KF-objectTracking
以kears-yolov3做detector,以Kalman-Filter算法做tracker,进行多人物目标追踪
GreenVegetables123/webapp
Docker Fundamentals Python Sample WebApp
GreenVegetables123/chinese_ocr
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
GreenVegetables123/helloworld
a simple code named helloworld
GreenVegetables123/mxnet_center_loss
implement center loss operator for mxnet