j-w-yun/optimizer-visualization
Visualize Tensorflow's optimizers.
This tool helps machine learning engineers and researchers understand how different optimization algorithms converge by visualizing their paths on a 2D surface. You input various Tensorflow optimizers and their learning rates, and it outputs animated GIFs showing how each optimizer adjusts variables to find a minimum. This is useful for anyone training neural networks and looking to grasp the nuances of optimizer behavior.
400 stars. No commits in the last 6 months.
Use this if you are a machine learning practitioner or student trying to visually compare how different gradient descent optimizers behave under various conditions.
Not ideal if you need to optimize a model with high-dimensional data or are looking for a tool to automatically select the best optimizer for your specific task.
Stars
400
Forks
56
Language
Python
License
MIT
Category
Last pushed
Mar 07, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/j-w-yun/optimizer-visualization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nschaetti/EchoTorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on...
metaopt/torchopt
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)