otfusion
by sidak
Model Fusion via Optimal Transport, NeurIPS 2020
AI summary
Model fusion
Model fusion via optimal transport to combine performance of multiple machine learning models
- stars
- 136
- forks
- 28
- watching
- 4
Similar projects
Found by comparing what the projects do, not just their names.
Segmentation model
A TensorFlow-based implementation of the SegNet segmentation algorithm, with modifications to address index unravel issues and support multiple features such as dilation and multi-resolution learning.
Model optimizer
Enables the creation of smaller neural network models through efficient pruning and quantization techniques
Memory optimizer for deep learning models
A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution
ott-jax/ott550
Optimal matcher
A JAX-based library for computing optimal transport problems in various settings
Traffic Optimizer
A framework for training reinforcement learning models to optimize traffic control and simulation
nvlabs/edm1.4K
Generative model framework
This project provides a set of tools and techniques to design and improve diffusion-based generative models.
Segmentation model
An implementation of SegNet architecture for semantic segmentation using tensorflow and keras.
Parallelism framework
A pretraining framework for large language models using 3D parallelism and scalable training techniques
Mixture of Experts Model
A large vision-language model using a mixture-of-experts architecture to improve performance on multi-modal learning tasks
Segment model
An implementation of a CNN model optimized for speed and segment anything functionality using the FastSAM design.
Machine learning textbook
A comprehensive guide to building machine learning models for streaming data in Python
Model trainer
Enables distributed deep learning with Keras and Spark for scalable model training
Image Segmentation Model
An implementation of a deep learning model for image segmentation using TensorFlow and Keras
Quantizer
A PyTorch quantization backend for models.
Optimization solver
A compiler and solver for optimization problems using zkSNARKs
