work-image-ai Goto Github PK

alpaca.cpp

Locally run an Instruction-Tuned Chat-Style LLM

chinese-ocr

[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

chinese_ocr

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

colossalai

Colossal-AI: A Unified Deep Learning System for Large-Scale Parallel Training

cordova-plugin-iflyspeech

科大讯飞的语音听说读写的cordova插件

cordova-plugin-speechrecognition

:microphone: Cordova Plugin for Speech Recognition

crnn.pytorch

Convolutional recurrent network in pytorch

crnn_chinese_characters_rec

chinese characters recognition

darknet

darknet深度学习框架源码分析：详细中文注释，涵盖框架原理与实现语法分析

darknet-1

Convolutional Neural Networks

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

eat_tensorflow2_in_30_days

Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

efficientdet-pytorch

A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights

ffmpeg.wasm

FFmpeg for browser and node, powered by WebAssembly

frcnn

Faster R-CNN / R-FCN :bulb: C++ version based on Caffe

google-neural-machine-translation-gnmt

It is a tensorflow implementation of GNMT

gpt2-chitchat

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI**)

image-similarity

计算图片之间的相似度

imagedetectioncordovaplugin

Image detection cordova plugin

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

keras_ocr

用keras实现OCR定位、识别

keymousego

类似按键精灵的鼠标键盘录制和自动化操作 模拟点击和键入 | automate mouse clicks and keyboard input

machine-learning

个人机器学习(Machine Learning, ML)笔记

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mobilenet-ssd

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

moire-pattern-detection

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。

nn-svg

Publication-ready NN-architecture schematics.

nowatermark

remove watermark. 去除图片中的水印