Images and video restoration in multiple-stages using MIRNETv2 model, additionally object detection on images and video through FASTER-RCNN . And complete web application in flask including responsive front-end
-
Updated
Dec 26, 2022
Images and video restoration in multiple-stages using MIRNETv2 model, additionally object detection on images and video through FASTER-RCNN . And complete web application in flask including responsive front-end
Welcome to the project on downloading the COCO dataset from a JSON file! This application was developed with one goal in mind: to provide an educational and entertaining solution for obtaining data from the famous COCO (Common Objects in Context) dataset.
Image Captioning model with resnet and GRU
Computer Vision Project
Demonstrates real-time object detection using the YOLOv8 pre-trained model. The script utilizes the YOLOv8 model to identify objects in a live video stream captured from the user's webcam.
Implementation of object detection in images using YOLO model and open CV.
This application eliminates a set of given elements from a serial video resource. You can directly set some classes and qualifications for filtering options also, there also exixst an sql output for schemes.
CNN based deep learning project for image segmentation
Yolov3 object detector using pre-trained model on coco dataset.
Something to do with Math I think
Decoding the Learned Features of Masked Autoencoders in Semantic Segmentation Tasks
YOLOv4 detection on COCO dataset using OpenCV DNN module, compiled with CUDA.
Implementation of CVPR 2020 paper "EfficientDet: Scalable and Efficient Object Detection" using PyTorch and OpenCV
Apply Albumentations to COCO Dataset
a full deep learning pipeline that generates captions for images using a CNN encoder & RNN decoder
You can get the subset(interested categories) from COCO dataset with Google Colab and gloucv library
Unsafe overtaking of large trucks is a major cause of traffic accidents and road congestion. Current solutions, such as Samsung's attempt to install screens on trucks, have been unsuccessful. There is a need for a reliable and accurate system to assist drivers in overtaking trucks safely.
Image captioning project with the COCO dataset.
Sanitize the FSOCO dataset to have the same structure as the COCO dataset.
Add a description, image, and links to the coco-dataset topic page so that developers can more easily learn about it.
To associate your repository with the coco-dataset topic, visit your repo's landing page and select "manage topics."