Deep neural network optimizer to make them faster, smaller, and energy-efficient from cloud to edge computing.
Project description
Neutrino Engine
Neutrino is a deep learning library for optimizing and accelerating deep neural networks to make them faster, smaller and more energy-efficient. Neural network designers can specify a variety of pre-trained models, datasets and target computation constraints and ask the engine to optimize the network. High-level APIs are provided to make the optimization process easy and transparent to the user. Neutrino can be biased to concentrate on compression (relative to disk size taken by the model) or latency (forward call’s execution time) optimization.
Community Release
Our community edition, provides many important features to experience the usability and the optimization power of Neutrino. Community edition is primarily targetted to verify the smooth integration of Neutrino into the existing process and pipeline of various products. Feel free
to use it! The aim of the community edition is multi-fold, as follows:
- Users could hands-on experience the power and capacity of model architecture optimization achieved using
Deeplite Neutrino
- Users could compare the performance obtained using
Deeplite Neutrino
with other open-source and industry model architecture optimization frameworks - Users could export an optimized model to test integration with their end applications
- Users could verify the integration of
Deeplite Neutrino
with their business-as-usual - Users could use
Deeplite Neutrino
to accelerate academic research and report results in research papers - Users could just play around with
Deeplite Neutrino
and enjoy the usability of model architecure optimization in various use-cases
For detailed comparison of features on our community and production editions, refer to the documentation
Installation
Use pip
to install neutrino-engine
from PyPi repository. We recommend creating a new python virtualenv, then pip install using the following commands.
pip install --upgrade pip
pip install neutrino-engine
pip install neutrino-torch
For other methods of installation and detailed instructions, refer to the documentation
Get Your Free Community License
The community license key is completely free-to-obtain and free-to-use. Fill out this simple form to obtain the license key for the Community Version of Deeplite Neutrino™.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distributions
Hashes for neutrino_engine-5.0.1-cp38-cp38-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 86d05eb0b00fffbcd3aa53840b6b133f730d79517b9c6d568a5140dbc9b11869 |
|
MD5 | 0534c38b942656fb6e4a1c6d01090335 |
|
BLAKE2b-256 | 4afbf5f21c7eb0dd73c1b069842990c59a3d8ebf62bea3118f95a439066d2260 |
Hashes for neutrino_engine-5.0.1-cp38-cp38-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5f6dd3459329b23c0fb8a2cd352d3e5b1999d069d2e61c19da00e20d43f74544 |
|
MD5 | a5487e974e3bfcc932f933990e8e9a0c |
|
BLAKE2b-256 | 32457bbc5c2f1c3d90556d66e1857349abfa1602546b48daff43f8653ded47ae |
Hashes for neutrino_engine-5.0.1-cp37-cp37m-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 699575d7b932bf4526523a950e73d39224d238832ac04caeea24d9977a855ddb |
|
MD5 | 099e18ed32563b613e417e1b8dfd3c67 |
|
BLAKE2b-256 | ce4237d55d81a5ca62ab2e7bc16a1b13fabdbae4634cd46363839dec495cb5dd |
Hashes for neutrino_engine-5.0.1-cp37-cp37m-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | cd083c8ca96098d885bfa123312c30d26cc7ecf19821b5a3409ed7416c62ac4a |
|
MD5 | 24d82e528a1fcdd2aede22de7db3ecee |
|
BLAKE2b-256 | ae80cab37f8cf32b078aa3e3d866c8742b51b275d64f503575ba79fb5e2f2b49 |
Hashes for neutrino_engine-5.0.1-cp36-cp36m-manylinux2010_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d5e5aa557bbab3e7473abc81a072f40f1be59490830d516ded405d1f20efe706 |
|
MD5 | 2fd025649d4544c98239a8260ab1c1b4 |
|
BLAKE2b-256 | 395d935347a059797d10f9ae67956413889f64366a3fc5b6d1cb49aa9902fd32 |
Hashes for neutrino_engine-5.0.1-cp36-cp36m-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 60c01ee846d25cd1dabd3e4e0b4996369e67aec3ac55d19804a6575c29bdfe80 |
|
MD5 | 2902c15b4ab455a404a26bbda3528f04 |
|
BLAKE2b-256 | dde3e59d9ae53629b81afa7efabd9d8206682bdc693f6a2e015da5fd704c19c5 |