kito · PyPI

Keras inference time optimizer

Project description

This code takes on input trained Keras model and optimize layer structure and weights in such a way that model became much faster (~10-30%), but works identically to initial model. It can be extremely useful in case you need to process large amount of images with trained model. Reduce operation was tested on all Keras models zoo. More details: https://github.com/ZFTurbo/Keras-inference-time-optimizer

Project details

Release history Release notifications | RSS feed

1.0.5

Sep 2, 2020

1.0.4

Apr 1, 2020

1.0.3

Sep 18, 2019

1.0.2

Dec 28, 2018

This version

1.0.1

Dec 20, 2018

1.0.0

Nov 30, 2018

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kito-1.0.1.tar.gz (8.2 kB view hashes)

Uploaded Dec 20, 2018 Source

Built Distribution

kito-1.0.1-py3-none-any.whl (10.1 kB view hashes)

Uploaded Dec 20, 2018 Python 3

Hashes for kito-1.0.1.tar.gz

Hashes for kito-1.0.1.tar.gz
Algorithm	Hash digest
SHA256	`4b8af6de55de8db15553ce31c40597943b5e2179cfc7d70ba2a31907b7937511`
MD5	`96c8f3ccd46350aead4303015436233a`
BLAKE2b-256	`e63bb504d09538b1df6a9520420cd0ecbeca77f9c08489662c2bd06d682978b2`

Hashes for kito-1.0.1-py3-none-any.whl

Hashes for kito-1.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`1c18d98da727b3e24477459f3f5b193ab4b34eda61206d0b50880b9f6782fc16`
MD5	`39f97bbf4b9b81bde95731a8a84f70a2`
BLAKE2b-256	`db9232728c27d41a0bb597e925113554ed877d1aa72dc9eaccefc9cac37a3a81`