clementchadebec/benchmark_VAE
A PyTorch library providing unified implementations of common Variational Autoencoder variants with benchmarking and experiment tracking capabilities.
Not currently ranked — collecting fresh signals.
star history
This library implements variational autoencoder models under a unified PyTorch framework, enabling benchmark experiments and fair comparisons across different VAE architectures. It supports training models with the same autoencoding neural network architecture, integrates with MLflow, wandb, and Comet for experiment monitoring, and allows model sharing via the HuggingFace Hub.
Frequently asked
- What is clementchadebec/benchmark_VAE?
- A PyTorch library providing unified implementations of common Variational Autoencoder variants with benchmarking and experiment tracking capabilities.
- Is benchmark_VAE open source?
- Yes — clementchadebec/benchmark_VAE is open source, released under the Apache-2.0 license.
- What language is benchmark_VAE written in?
- clementchadebec/benchmark_VAE is primarily written in Python.
- How popular is benchmark_VAE?
- clementchadebec/benchmark_VAE has 2k stars on GitHub.
- Where can I find benchmark_VAE?
- clementchadebec/benchmark_VAE is on GitHub at https://github.com/clementchadebec/benchmark_VAE.