Deepstream ProjectThis is a highly separated deployment project based on Deepstream , including the full range of Yolo and continuously expanding deployment projects such as Ocr.
Stars: ✭ 120 (+179.07%)
BankCard-RecognizerIdentifying numbers from bankcard, based on Deep Learning with Keras [China Software Cup 2019]
Stars: ✭ 74 (+72.09%)
Mobilenet YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
Stars: ✭ 1,566 (+3541.86%)
crnn.gluonA gluon re-implementation of Convolutional recurrent network in gluon
Stars: ✭ 21 (-51.16%)
Text rendererGenerate text images for training deep learning ocr model
Stars: ✭ 931 (+2065.12%)
Nanodet⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
Stars: ✭ 3,640 (+8365.12%)
EasyocrReady-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Stars: ✭ 13,379 (+31013.95%)
Tf CrnnTensorFlow convolutional recurrent neural network (CRNN) for text recognition
Stars: ✭ 275 (+539.53%)
Video2xA lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018.
Stars: ✭ 3,760 (+8644.19%)
insightocrMXNet OCR implementation. Including text recognition and detection.
Stars: ✭ 100 (+132.56%)
CrnnCRNN(Convolutional Recurrent Neural Network), with optional STN(Spatial Transformer Network), in Tensorflow, multi-gpu supported.
Stars: ✭ 34 (-20.93%)
PaddleocrAwesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
Stars: ✭ 18,084 (+41955.81%)
TrFree Offline OCR 离线的中文文本检测+识别SDK
Stars: ✭ 598 (+1290.7%)
DeepdetectDeep Learning API and Server in C++14 support for Caffe, Caffe2, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
Stars: ✭ 2,306 (+5262.79%)
ModelfeastPytorch model zoo for human, include all kinds of 2D CNN, 3D CNN, and CRNN
Stars: ✭ 116 (+169.77%)
InferenceHelperC++ Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, OpenVINO, ncnn, MNN, SNPE, Arm NN, NNabla, ONNX Runtime, LibTorch, TensorFlow
Stars: ✭ 142 (+230.23%)
ClothingTransfer-NCNNCT-Net, OpenPose, LIP_JPPNet, DensePose running with ncnn⚡服装迁移/虚拟试穿⚡ClothingTransfer/Virtual-Try-On⚡
Stars: ✭ 166 (+286.05%)
crnn一个基于TensorFlow2的CRNN项目
Stars: ✭ 47 (+9.3%)
Pottan OcrA stupid OCR for malayalam language
Stars: ✭ 39 (-9.3%)
CRNN.tf2Convolutional Recurrent Neural Network(CRNN) for End-to-End Text Recognition - TensorFlow 2
Stars: ✭ 131 (+204.65%)
TensorrtxImplementation of popular deep learning networks with TensorRT network definition API
Stars: ✭ 3,456 (+7937.21%)
AESRC2020a deep accent recognition network
Stars: ✭ 35 (-18.6%)
Keras Textclassification中文长文本分类、短句子分类、多标签分类、两句子相似度(Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short),字词句向量嵌入层(embeddings)和网络层(graph)构建基类,FastText,TextCNN,CharCNN,TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN
Stars: ✭ 914 (+2025.58%)
crnn.mxnetcrnn in mxnet.can train with chinese characters
Stars: ✭ 47 (+9.3%)
CRNN-OCR-liteLightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
Stars: ✭ 130 (+202.33%)
YOLOXYOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Stars: ✭ 6,570 (+15179.07%)
Crnn.pytorchcrnn实现水平和垂直方向中文文字识别, 提供在3w多个中文字符训练的水平识别和垂直识别的预训练模型; 欢迎关注,试用和反馈问题... ...
Stars: ✭ 145 (+237.21%)
TnnTNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and …
Stars: ✭ 3,257 (+7474.42%)
Ncnnncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+31006.98%)
Pytorchocr基于pytorch的ocr算法库,包括 psenet, pan, dbnet, sast , crnn
Stars: ✭ 198 (+360.47%)
Chineseocr lite超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
Stars: ✭ 8,295 (+19190.7%)
Lstm ctc ocrUse CTC + tensorflow to OCR
Stars: ✭ 365 (+748.84%)
Waifu2x Extension GuiVideo, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, SRMD, RealSR, Anime4K, RIFE, CAIN, DAIN, and ACNet.
Stars: ✭ 5,463 (+12604.65%)
SightseqComputer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (+169.77%)
CrnnA TensorFlow implementation of https://github.com/bgshih/crnn
Stars: ✭ 287 (+567.44%)
lite.ai.toolkit🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOX, YOLOP, MODNet, YOLOR, NanoDet, YOLOX, SCRFD, YOLOX . MNN, NCNN, TNN, ONNXRuntime, CPU/GPU.
Stars: ✭ 1,354 (+3048.84%)
Text DetectorTool which allow you to detect and translate text.
Stars: ✭ 173 (+302.33%)
Cortex License Plate Reader ClientA client to connect to cortex-provisioned infrastructure on AWS to do license plate identification in real time.
Stars: ✭ 268 (+523.26%)
cain-ncnn-vulkanCAIN, Channel Attention Is All You Need for Video Frame Interpolation implemented with ncnn library
Stars: ✭ 85 (+97.67%)
Crnn With Stnimplement CRNN in Keras with Spatial Transformer Network
Stars: ✭ 83 (+93.02%)
ssd detectorsSSD-based object and text detection with Keras, SSD, DSOD, TextBoxes, SegLink, TextBoxes++, CRNN
Stars: ✭ 295 (+586.05%)
Ocr.pytorchA pure pytorch implemented ocr project including text detection and recognition
Stars: ✭ 196 (+355.81%)
NhyaiAI智能审查,支持色情识别、暴恐识别、语言识别、敏感文字检测和视频检测等功能,以及各种OCR识别能力,如身份证、驾照、行驶证、营业执照、银行卡、手写体、车牌和名片识别等功能,可以访问网站体验功能。
Stars: ✭ 60 (+39.53%)