Pinned Repositories
AllYouNeedToKnowAboutX
A collection of tips for students, developers, and teachers.
DLwDefectIntro
Introduction of defect/aoi classification with common NN model.
HuWeiSPClassification
An Inception-v3 application for CCTV image classification.
ImageShapFinder
Finding object's location in image with different shap (rectangle, circle, triangle, etc.)
iSeeWater
a flood detection system using CNN model to inference CCTV cameras
JVZY
Optical Character Recognition (OCR) [3] technology has also been greatly improved, so the digitization of document has reached the highest efficiency. However, since the texts of K-4 period will have phonetic symbols annotated to facilitate pronunciation learning, the original OCR efficiency will be affected when these phonetic characters are digitized. So, the essential premise is that there needs to be an appropriate number of phonetic symbol datasets for retraining the OCR model and training a phonetic symbols detector for image inpainting.
NCHCCROP
A very old distributed image split/crop tool by Bash and ImageMagick.
rpi_edge_flood
利用樹梅派建立邊緣裝置用於淹水監控
vscv.github.io
visual sensing and computer vision
vscv's Repositories
vscv/AllYouNeedToKnowAboutX
A collection of tips for students, developers, and teachers.
vscv/DLwDefectIntro
Introduction of defect/aoi classification with common NN model.
vscv/iSeeWater
a flood detection system using CNN model to inference CCTV cameras
vscv/HuWeiSPClassification
An Inception-v3 application for CCTV image classification.
vscv/ImageShapFinder
Finding object's location in image with different shap (rectangle, circle, triangle, etc.)
vscv/JVZY
Optical Character Recognition (OCR) [3] technology has also been greatly improved, so the digitization of document has reached the highest efficiency. However, since the texts of K-4 period will have phonetic symbols annotated to facilitate pronunciation learning, the original OCR efficiency will be affected when these phonetic characters are digitized. So, the essential premise is that there needs to be an appropriate number of phonetic symbol datasets for retraining the OCR model and training a phonetic symbols detector for image inpainting.
vscv/NCHCCROP
A very old distributed image split/crop tool by Bash and ImageMagick.
vscv/rpi_edge_flood
利用樹梅派建立邊緣裝置用於淹水監控
vscv/vscv.github.io
visual sensing and computer vision
vscv/csc
中鋼人工智慧挑戰賽 - 字元辨識
vscv/DeepLearningExamples
Deep Learning Examples
vscv/utils_for_tfodapiv2
This 100% Glue Code is for procesing image/annotation/visualizaiton/traing_set/CSV when working on TF OD API v2.
vscv/3D_detection
vscv/3DUnetCNN
Keras 3D U-Net Convolution Neural Network (CNN) designed for medical image segmentation
vscv/AI-Services
here is AI Service samples
vscv/compmirrors
vscv/darkflow
Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices
vscv/DAS
Testing note when playing DAS
vscv/efficientnet
Implementation of EfficientNet model. Keras and TensorFlow Keras.
vscv/fork-Tbrain_2023houseprice
vscv/fork_Variations-of-SFANet-for-Crowd-Counting
The official implementation of "Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting"
vscv/HET-MC
vscv/install-latex-guide-zh-cn
一份简短的关于 LaTeX 安装的介绍
vscv/jiwer
Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
vscv/MMSLAB-TF2
MMSLAB-TF2-Lab
vscv/object-detection-api
Make it easy to train and deploy Object Detection(SSD) and Image Segmentation(Mask R-CNN) Model Using TensorFlow Object Detection API.
vscv/TBrain-2023-SinoPac-AIGO-House-Price-Prediction
1st place solution for TBrain 2023 SinoPac AIGO House Price Prediction 永豐AI GO競賽-攻房戰 第一名解法
vscv/Tools-to-Design-or-Visualize-Architecture-of-Neural-Network
Tools to Design or Visualize Architecture of Neural Network
vscv/tpu
Reference models and tools for Cloud TPUs.
vscv/visdom
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.