AroMorin/DNNOP
Deep Neural Network Optimization Platform with Gradient-based, Gradient-Free Algorithms
This platform helps AI/ML engineers and researchers efficiently train deep neural networks. It provides a selection of neural network architectures and optimization algorithms, both traditional gradient-based methods like SGD and newer gradient-free approaches. You input your problem framed as an 'environment' and a neural network model, and it outputs an optimized, trained neural network capable of solving that task.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking for a flexible toolkit to experiment with different deep neural network architectures and training algorithms for tasks like image classification or reinforcement learning.
Not ideal if you are an end-user without deep learning expertise looking for a ready-to-use application, as this requires coding and a strong understanding of neural network training.
Stars
12
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jan 13, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AroMorin/DNNOP"
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)