Projet d'optimisation, M2 AIC 2018-2019
-
Updated
Oct 19, 2018 - C++
Projet d'optimisation, M2 AIC 2018-2019
A deep learning–based computer vision training pipeline for car damage detection using a Co-DETR learner enhanced with CBAM Attention, Hybrid Loss, and Albumentations. Trains on Colab to identify and localize car body defects such as scratches, dents, and rust. Includes end-to-end model training and quantitative evaluation.
Identify pigs in the camera footage and localize them using bounding boxes.
Scripts and tools for Pascal VOC/COCO/YOLO
VisionConverter is a Python library designed to convert object detection dataset annotations between the most widely used formats in computer vision. Allows developers to do conversions both from the command line and directly in Python code.
A python script to acces DSK JVC Tandy Color Computer files
A 100% offline, vanilla-JS invoice annotation tool with in-browser OCR (Tesseract.js). Draw tight boxes for buyer/seller/meta/line items; the app OCRs each region, writes values into your JSON at the correct paths, and exports updated data plus training artifacts (labels JSON, COCO, annotated PNG). No servers, no frameworks.
PASCAL VOC 2007 dataset converted into COCO JSON format
Image depth and body keypoints detection demo app, written in Python.
Create a YOLO-format subset of the COCO dataset
[DONE] Instructional project to demo a (very) simple Run Loop, here in a "game".
Image Captioning Project using CNN-RNN architecture
A Web based Image Classifier using Cifar10 that has 10 classes-based dataset and creating a neural network then deploying it directly to web interface using Taipy which is an open-source Python library for building production-ready web applications front-end & back-end.
mask-to-annotation is a powerful and efficient tool for automatically generating annotations in popular computer vision formats such as COCO, YOLO, and VGG from saliency masks.
example for fifyone with coco pose polyline
Add a description, image, and links to the coco topic page so that developers can more easily learn about it.
To associate your repository with the coco topic, visit your repo's landing page and select "manage topics."