pytorch implementation of a WACV 2021 Paper "Class-agnostic Few-shot-Object-Counting"
-
Updated
Sep 22, 2022 - Python
pytorch implementation of a WACV 2021 Paper "Class-agnostic Few-shot-Object-Counting"
this simple tutorial will introduce how to use im2rec for mx.image.ImageIter , ImageDetIter and how to use im2rec for COCO DataSet
Cityscapes to CoCo Format Conversion Tool for Mask-RCNN and Detectron
A CLI tool can create a specific task-dataset you want based on COCO dataset. Given the annotation JSON file, this tool will help you download the data and set the symbolic links from data_dir to task_dir !!
LabelFree
Image Captioning using CNN and Transformer.
Tool to convert all labelme keypoints file to one single coco keypoints file
Convert the predicted annotated text into voice responses
Automatic Image Captioning using PyTorch on MS COCO dataset
Clone of COCO API - Dataset @ http://cocodataset.org/ - with changes to support Windows build and python3
Use the python script to select images contains person in the COCO。
A tool for the conversion from ICDAR to COCO dataset.
YOLOX implemented by pytorch lightning, a simpler expression of pytorch
Live object detection using MobileNetSSD with OpenCV
Build a subset of COCO dataset
An object detection model that uses YOLOv5 and OpenCV
Pose Estimation using Ultralytics YOLOv8 engine
This is PyQt platform where the selected image is processed by using YOLOv3 algorithm and darknet framework.
This repository tackles traffic congestion in smart cities using computer vision. The system automatically detects and classifies vehicles, analyzes traffic density, and dynamically adjusts traffic lights - all to optimize traffic flow!
Here a transfer learning solution for traffic light detection is presented. It uses Mask Region-Based Convolutional Neural Network as it base.
Add a description, image, and links to the cocodataset topic page so that developers can more easily learn about it.
To associate your repository with the cocodataset topic, visit your repo's landing page and select "manage topics."