jxbz/fromage

🧀 Pytorch code for the Fromage optimiser.

/ 100

Emerging

Fromage is an optimization algorithm designed to improve the training of deep neural networks. It takes your existing neural network architecture and training data, and provides a more stable and potentially better-performing way to update the network's internal parameters. This tool is for machine learning researchers and practitioners who are building and training deep learning models, particularly for tasks like image classification or natural language processing.

129 stars. No commits in the last 6 months.

Use this if you are training deep neural networks with PyTorch and want to explore an alternative optimization method to potentially achieve better or more stable results, especially for tasks like image classification or text generation.

Not ideal if you are not using PyTorch for deep learning, or if you need an optimizer specifically designed for very large-scale, distributed training setups without local code modifications.

deep-learning-optimization neural-network-training image-classification natural-language-processing machine-learning-research

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 10 / 25

Maturity 16 / 25

Community 10 / 25

How are scores calculated?

Stars

129

Forks

Language

Jupyter Notebook

License

—

Higher-rated alternatives

dataflowr/notebooks

code for deep learning courses

jeffheaton/app_deep_learning

T81-558: PyTorch - Applications of Deep Neural Networks @Washington University in St. Louis

dvgodoy/PyTorchStepByStep

Official repository of my book: "Deep Learning with PyTorch Step-by-Step: A Beginner's Guide"

xl0/lovely-tensors

Tensors, for human consumption

rentruewang/koila

Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.

Explore ML Frameworks

All categories Trending ML Framework directory Insights