LatentViewer is a visualisation tool to inspect image embeddings. It uses principal component analysis to display the embedding vectors as a point cloud. Individual points can be selected to display an image, as well as its nine closest neighbours.
Additionally, there is the possibility to train an SVM classifier through an active learning method. This is particularly useful when dealing with embeddings of an unlabeled data set.
Install the latent viewer with pip:
pip install latent-viewer
After installation, the latent-viewer can be invoked with lv.
For using, it is important to specify both a file with the embeddings, as well as an HDF5 image archive.
lv -e embeddings.csv -a image_archive.hdf5
FAQs
An interactive 3D viewer for inspecting image embeddings
We found that latent-viewer demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
/Security News
A flawed sandbox in @nestjs/devtools-integration lets attackers run code on your machine via CSRF, leading to full Remote Code Execution (RCE).
Product
Customize license detection with Socket’s new license overlays: gain control, reduce noise, and handle edge cases with precision.
Product
Socket now supports Rust and Cargo, offering package search for all users and experimental SBOM generation for enterprise projects.