uber/neuropod
A uniform interface to run deep learning models from multiple frameworks
This is a tool for machine learning engineers and researchers who build and deploy deep learning models. It provides a consistent way to run models created in various frameworks like TensorFlow or PyTorch. You feed it a trained deep learning model, and it allows you to integrate and run that model in your application using a single, unified interface, regardless of the original framework.
940 stars. No commits in the last 6 months.
Use this if you manage or deploy deep learning models from different frameworks and need a standardized way to integrate them into your production systems or research pipelines.
Not ideal if you only work with models from a single deep learning framework and don't require interoperability or standardized deployment.
Stars
940
Forks
73
Language
C++
License
Apache-2.0
Category
Last pushed
Jan 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/uber/neuropod"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.