Compositional Sketch Search

Last update: Sep 06, 2021

Related tags

Deep Learning compsketch

Overview

Compositional Sketch Search

Official repository for ICIP 2021 Paper: Compositional Sketch Search

Requirements

Install and activate conda environment

conda env create -f env.yml
conda activate compsketch
cd src

If you're having trouble with installation, try changing faiss-gpu to faiss-cpu in env.yml.

Indexing

Either download faiss index for OpenImages or Unsplash indexes here and place them in indexes/ or index your own dataset like so:

python indexing.py --root PathToImages --name IndexName

Searching

Run the streamlit app

streamlit run streamlit_app.py

If you are using a custom dataset:

Pick 'Custom' in the Dataset selection box.
Pick index file in the second selection box.
Paste the same dataset root you used during indexing.

Sketch objects, using one colour per object. Press "Search" to see results!

Troubleshooting

On a Mac, I had to run this command to make it work

export KMP_DUPLICATE_LIB_OK=TRUE

Owner

Alexander Black

PhD student at University of Surrey CVSSP | Adobe Content Authenticity Initiative - Video Content Authenticity

GitHub Repository

Cross-Modal Contrastive Learning for Text-to-Image Generation

Cross-Modal Contrastive Learning for Text-to-Image Generation This repository hosts the open source JAX implementation of XMC-GAN. Setup instructions

94 Nov 12, 2022

Implementation for the "Surface Reconstruction from 3D Line Segments" paper.

Surface Reconstruction from 3D Line Segments Surface reconstruction from 3d line segments. Langlois, P. A., Boulch, A., & Marlet, R. In 2019 Internati

85 Jan 04, 2023

Gradient Inversion with Generative Image Prior

Gradient Inversion with Generative Image Prior This repository is an implementation of "Gradient Inversion with Generative Image Prior", accepted to N

25 Jan 09, 2023

pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Unofficial implementation: MoCo: Momentum Contrast for Unsupervised Visual Representation Learning (Paper) InsDis: Unsupervised Feature Learning via N

16 Nov 04, 2020

Python scripts to detect faces in Python with the BlazeFace Tensorflow Lite models

Python scripts to detect faces using Python with the BlazeFace Tensorflow Lite models. Tested on Windows 10, Tensorflow 2.4.0 (Python 3.8).

46 Nov 17, 2022

Official implementation for paper: Feature-Style Encoder for Style-Based GAN Inversion

Feature-Style Encoder for Style-Based GAN Inversion Official implementation for paper: Feature-Style Encoder for Style-Based GAN Inversion. Code will

63 Jan 03, 2023

A tensorflow implementation of Fully Convolutional Networks For Semantic Segmentation

##A tensorflow implementation of Fully Convolutional Networks For Semantic Segmentation. #USAGE To run the trained classifier on some images: python w

13 Nov 17, 2022

Voice assistant - Voice assistant with python

🌐 Python Voice Assistant 🌵 - User's greeting 🌵 - Writing tasks to todo-list ?

10 Dec 26, 2022

Autoencoders pretraining using clustering

2 Dec 16, 2021

ObjectDetNet is an easy, flexible, open-source object detection framework

Getting started with the ObjectDetNet ObjectDetNet is an easy, flexible, open-source object detection framework which allows you to easily train, resu

5 Aug 25, 2020

Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

InfoPro-Pytorch The Information Propagation algorithm for training deep networks with local supervision. (ICLR 2021) Revisiting Locally Supervised Lea

78 Dec 27, 2022

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representation from common sense knowledge graphs.

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representa

94 Nov 21, 2022

Compositional Sketch Search

Related tags

Overview

Compositional Sketch Search

Requirements

Indexing

Searching

Troubleshooting

Owner

Alexander Black

Cross-Modal Contrastive Learning for Text-to-Image Generation

Implementation for the "Surface Reconstruction from 3D Line Segments" paper.

Gradient Inversion with Generative Image Prior

pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Python scripts to detect faces in Python with the BlazeFace Tensorflow Lite models

Official implementation for paper: Feature-Style Encoder for Style-Based GAN Inversion

A tensorflow implementation of Fully Convolutional Networks For Semantic Segmentation

Voice assistant - Voice assistant with python

Autoencoders pretraining using clustering

ObjectDetNet is an easy, flexible, open-source object detection framework

Learning recognition/segmentation models without end-to-end training. 40%-60% less GPU memory footprint. Same training time. Better performance.

Generative Flow Networks for Discrete Probabilistic Modeling

3D dataset of humans Manipulating Objects in-the-Wild (MOW)

Real-time object detection on Android using the YOLO network with TensorFlow

The pure and clear PyTorch Distributed Training Framework.

ComputerVision - This repository aims at realized easy network architecture

Official repository for Natural Image Matting via Guided Contextual Attention

🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.

NOMAD - A blackbox optimization software

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representation from common sense knowledge graphs.