How to cluster images based on visual similarity | by Gabe Flomo | Towards Data Science

Use a pre-trained neural network for feature extraction and cluster images using K-means.

How to cluster images based on visual similarity | Towards Data Science Machine Learning How to cluster images based on visual similarity Use a pre-trained neural network for feature extraction and cluster images using K-means. Gabe Flomo Sep 29, 2020 5 min read Share Photo by Pietro Jeng on Unsplash Objective In this tutorial, I’m going to walk you through using a pre-trained neural network to extract a feature vector from images and cluster the images based on how similar the feature vectors are. The model The pre-trained model that will be used in this tutorial is the VGG16 convolutio

saved by

• Jackie Ni

related reading

• Feature Visualizationdistill.pub
• Feature Visualizationdistill.pub
• lecture_2.pdfcs231n.stanford.edu
• Faiss: A library for efficient similarity search - Engineering at Metaengineering.fb.com
• GitHub - zhoushengisnoob/DeepClustering: Methods and Implements of Deep Clusteringgithub.com
• k-means clustering - Wikipediaen.wikipedia.org
• Vector embeddings | OpenAI APIdevelopers.openai.com
• Convolutional Neural Network (CNN) | TensorFlow Coretensorflow.org
• ImageNet Classification with Deep Convolutional Neural Networksproceedings.neurips.cc
• GitHub - facebookresearch/faiss: A library for efficient similarity search and clustering of dense vectors.github.com
• Vector embeddings | OpenAI APIplatform.openai.com
• the-algorithm/src/scala/com/twitter/simclusters_v2/README.md at main · twitter/the-algorithmgithub.com