It is a simple application that utilizes Convolutional AutoEncoder for extracting latent features by doing unsupervised training on CIFAR-10 dataset. After the Images are transformed using the Encoder part of ConvAutoEncoder into 512-D vector, ANN is used to find similar images as the given one. The Code for extracting features is inside CIFAR_CAE.ipynb that will save the trained model as ConvAutoEncoder.h5. Code for similar image-search using ANN is inside ImageSearch. Pre-trained is provided in the repo, choose to use that or else train your own model by changing hyperparameters.
-
Notifications
You must be signed in to change notification settings - Fork 0
Simple Image Searching on CIFAR10 dataset using Conv Autoencoder
License
Saurabh1496/Image-Search
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Simple Image Searching on CIFAR10 dataset using Conv Autoencoder
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published