A python package to perform same transformation to coco-annotation as performed on the image.

Overview

coco-transform-util

A python package to perform same transformation to coco-annotation as performed on the image.

Installation

Way 1

$ git clone https://git.cglcloud.com/ILC-APAC/coco-transform-util.git
$ cd coco-transform-util
$ python3 setup.py install

Way 2

$ pip3 install git+https://git.cglcloud.com/ILC-APAC/coco-transform-util.git
<<< Username: <[email protected]>
<<< Password: <personal access token or SSH key>

Personal Access token looks like this 83b318cg875a5g302e5fdaag74afc8ceb6a91a2e.

Reference: How to generate Personal Access token

Check installation

import ctu
print(ctu.__version__)

Benefits and Use Cases

  1. Faster Model Training: Decrease the size of images and accordingly its annotation will be changed using this.
  2. Flexibility: Rescaling of images and annotations to meet the need of Model/Framework.
  3. Cost Saving: Lesser Computation requirement as images can be downscaled.
  4. Interpretability: Annotation Visualization is also a part of this package.
  5. Data Augmentation: <more practical in future>
  6. Ability to handle other cases: Added Functionality such as cropping or padding of the annotation can help in multiple other cases such as:
    • cropping out each object image & annotation from an original image
    • cropping unnecessary area to zoom in on some particular area.
    • converting images to 1:1 aspect ratio by using padding and/or cropping.

How to use it?

Core

There are four core modules inside that helps in performing operations on COCO Annotation. These can imported as shown below:

from ctu import WholeCoco2SingleImgCoco, Coco2CocoRel, CocoRel2CocoSpecificSize, AggreagateCoco  

It's recommended that you have look at samples/example_core_modules.py to understand and explore how to use these.

Wrapper

Making use of wrappers can also come in handly to perform multiple operations in a much simpler and interpretable manner using the functions provided below:

from ctu import (
    sample_modif_step_di, get_modif_imag, get_modif_coco_annotation, 
    accept_and_process_modif_di, ImgTransform, Visualize
)

It's recommended that you have look at samples/example_highlevel_function.py to understand and explore how to use these.

Some sample data has also been provided with this package at example_data/* to explore these functionalities.

Demo / Sample

A sample HTML created from Jupyter-Notebook, contating some sample results has been added to the path samples/Demo-SampleOutput.html.

Version History

  • v0.1: Core Modules: WholeCoco2SingleImgCoco, Coco2CocoRel, CocoRel2CocoSpecificSize. External Dependency on AMLEET package.
  • v0.2: Removed the dependency on AMLEET package. Develop Core Module: AggreagateCoco. Addition of field "area" under "annotations" in coco.
  • v0.3: Completed: Remove the out of frame coordinates in annotation. Update & add fields in "annotation" > "images". Ability to create transparent and general mask create_mask. In Development: Ability to export transformed image, mask and annotation per image wise and as a whole too.

Future

  • Update the image fields in "images" key. (done)
  • Crop out the annotation which are out-of-frame based on recent image shape. (done)
  • Annotation Visualization + Mask creation can become a core feature to this library. (done)
  • Rotate 90 degree left/right.
  • Flip horizontally or vertically.
  • COCO to other annotation format can also be a feature to this package.
Code for Discriminative Sounding Objects Localization (NeurIPS 2020)

Discriminative Sounding Objects Localization Code for our NeurIPS 2020 paper Discriminative Sounding Objects Localization via Self-supervised Audiovis

51 Dec 11, 2022
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning, CVPR 2021

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning By Zhenda Xie*, Yutong Lin*, Zheng Zhang, Yue Ca

Zhenda Xie 293 Dec 20, 2022
Physics-Informed Neural Networks (PINN) and Deep BSDE Solvers of Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

NeuralPDE NeuralPDE.jl is a solver package which consists of neural network solvers for partial differential equations using scientific machine learni

SciML Open Source Scientific Machine Learning 680 Jan 02, 2023
Custom Implementation of Non-Deep Networks

ParNet Custom Implementation of Non-deep Networks arXiv:2110.07641 Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun Official Repository https

Pritama Kumar Nayak 20 May 27, 2022
GemNet model in PyTorch, as proposed in "GemNet: Universal Directional Graph Neural Networks for Molecules" (NeurIPS 2021)

GemNet: Universal Directional Graph Neural Networks for Molecules Reference implementation in PyTorch of the geometric message passing neural network

Data Analytics and Machine Learning Group 124 Dec 30, 2022
This repository contains the code for the paper "Hierarchical Motion Understanding via Motion Programs"

Hierarchical Motion Understanding via Motion Programs (CVPR 2021) This repository contains the official implementation of: Hierarchical Motion Underst

Sumith Kulal 40 Dec 05, 2022
Transformer in Vision

Transformer-in-Vision Recent Transformer-based CV and related works. Welcome to comment/contribute! Keep updated. Resource SCENIC: A JAX Library for C

Yong-Lu Li 1.1k Dec 30, 2022
CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation

CDGAN CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation CDGAN Implementation in PyTorch This is the imple

Kancharagunta Kishan Babu 6 Apr 19, 2022
A novel Engagement Detection with Multi-Task Training (ED-MTT) system

A novel Engagement Detection with Multi-Task Training (ED-MTT) system which minimizes MSE and triplet loss together to determine the engagement level of students in an e-learning environment.

Onur Çopur 12 Nov 11, 2022
Medical Image Segmentation using Squeeze-and-Expansion Transformers

Medical Image Segmentation using Squeeze-and-Expansion Transformers Introduction This repository contains the code of the IJCAI'2021 paper 'Medical Im

askerlee 172 Dec 20, 2022
Pytorch implementation of the paper "Topic Modeling Revisited: A Document Graph-based Neural Network Perspective"

Graph Neural Topic Model (GNTM) This is the pytorch implementation of the paper "Topic Modeling Revisited: A Document Graph-based Neural Network Persp

Dazhong Shen 8 Sep 14, 2022
offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021

LifelongReID Offical implementation of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021 by Nan Pu, Wei Chen, Yu L

PeterPu 76 Dec 08, 2022
Official implementation of UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation

UTNet (Accepted at MICCAI 2021) Official implementation of UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation Introduction Transf

110 Jan 01, 2023
An implementation of the proximal policy optimization algorithm

PPO Pytorch C++ This is an implementation of the proximal policy optimization algorithm for the C++ API of Pytorch. It uses a simple TestEnvironment t

Martin Huber 59 Dec 09, 2022
RoboDesk A Multi-Task Reinforcement Learning Benchmark

RoboDesk A Multi-Task Reinforcement Learning Benchmark If you find this open source release useful, please reference in your paper: @misc{kannan2021ro

Google Research 66 Oct 07, 2022
LAnguage Model Analysis

LAMA: LAnguage Model Analysis LAMA is a probe for analyzing the factual and commonsense knowledge contained in pretrained language models. The dataset

Meta Research 960 Jan 08, 2023
QMagFace: Simple and Accurate Quality-Aware Face Recognition

Quality-Aware Face Recognition 26.11.2021 start readme QMagFace: Simple and Accurate Quality-Aware Face Recognition Research Paper Implementation - To

Philipp Terhörst 59 Jan 04, 2023
Code release for "BoxeR: Box-Attention for 2D and 3D Transformers"

BoxeR By Duy-Kien Nguyen, Jihong Ju, Olaf Booij, Martin R. Oswald, Cees Snoek. This repository is an official implementation of the paper BoxeR: Box-A

Nguyen Duy Kien 111 Dec 07, 2022
Code to generate datasets used in "How Useful is Self-Supervised Pretraining for Visual Tasks?"

Synthetic dataset rendering Framework for producing the synthetic datasets used in: How Useful is Self-Supervised Pretraining for Visual Tasks? Alejan

Princeton Vision & Learning Lab 21 Apr 29, 2022
PyTorch implementation of U-TAE and PaPs for satellite image time series panoptic segmentation.

Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks (ICCV 2021) This repository is the official implem

71 Jan 04, 2023