zs's repositories
AttentionOCR
Scene text recognition
AutoAugment
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow
caffe-yolov3
A real-time object detection framework of Yolov3 based on caffe
Caffe_SSD_LSTM_LPR
基于SSD+Resnet+CTC的中文车牌检测识别
chinese_ocr
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
chineseocr
yolo3+ocr
chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn推理 , psenet(8.5M) + crnn(6.3M) + anglenet(1.5M) 总模型仅17M
cppkafka-examples
Modern C++ Kafka Examples
DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
deepstream_python_apps
A project demonstrating use of Python for DeepStream sample apps given as a part of SDK (that are currently in C,C++).
face.evoLVe.PyTorch
🔥🔥High-Performance Face Recognition Library on PyTorch🔥🔥
facerec-cpp
C++ Face Recognition
FFmpeg-patch
This repository contains a collection of FFmpeg* patches and samples to enable CNN model based video analytics capabilities (such as object detection, classification, recognition) in FFmpeg* framework.
gst-video-analytics
This repository contains a collection of GStreamer* elements to enable CNN model based video analytics capabilities (such as object detection, classification, recognition) in GStreamer* framework.
gstopencvfilter
A GStreamer video filter that uses OpenCV
gstreamer-1
Getting started with Gstreamer with C++
hello-algo
《Hello 算法》:动画图解、一键运行的数据结构与算法教程,支持 Java, C++, Python, Go, JS, TS, C#, Swift, Rust, Dart, Zig 等语言。
keras-yolo3
A Keras implementation of YOLOv3 (Tensorflow backend)
MTCNN_LibTorch
face detect
MultiRunner
This is a python package for multi-process running.
NVIDIA-Deepstream-Azure-IoT-Edge-on-a-NVIDIA-Jetson-Nano
This is a sample showing how to do real-time video analytics with NVIDIA DeepStream connected to Azure via Azure IoT Edge. It uses a NVIDIA Jetson Nano device that can process up to 8 real-time video streams concurrently.
OCR_CNN_-CTC
使用CNN全卷积神经网络进行整行汉字识别,正确率90-94%,后来有朋友改成densenet做主网络,做到99%以上正确率
tensorrt_demos
Some examples demonstrating how to optimize caffe/tensorflow/darknet models with TensorRT and run real-time inferencing with the optimized TensorRT engines
yolov3-channel-and-layer-pruning
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝,通道剪枝,知识蒸馏