Latte: Cross-framework Python Package for Evaluation of Latent-Based Generative Models
This provides a tool for researchers and practitioners in machine learning to standardize evaluations across frameworks, but it is incremental as it builds on existing evaluation methods.
The authors introduced Latte, a Python library for evaluating latent-based generative models, focusing on disentanglement learning and controllable generation, which is compatible with PyTorch and TensorFlow/Keras and ensures reproducible metric calculations.
Latte (for LATent Tensor Evaluation) is a Python library for evaluation of latent-based generative models in the fields of disentanglement learning and controllable generation. Latte is compatible with both PyTorch and TensorFlow/Keras, and provides both functional and modular APIs that can be easily extended to support other deep learning frameworks. Using NumPy-based and framework-agnostic implementation, Latte ensures reproducible, consistent, and deterministic metric calculations regardless of the deep learning framework of choice.