Named VGG feature extraction
Project description
Provides a version of the popular VGG networks that can be used as feature extractors similar to how to query nodes in tensorflow. Useful for style transfer code, where you want to do stuff like r11, r31, r51 = net.forward(targets=['relu1_1', 'relu3_1', 'relu5_1']). Also provides simple way to load normalized weights as in Gatys et al.
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 Distribution
pytorch-vgg-named-0.3.tar.gz
(5.7 kB
view hashes)
Built Distribution
Close
Hashes for pytorch_vgg_named-0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7c6e23762058de8f70e19121ba9ed9becc642372fbda2b28569303e0984ac4a9 |
|
MD5 | 36de77c0959534cd306ca9ad66ca1253 |
|
BLAKE2b-256 | 591342f9b99e264614a5e2435148064d6fb16b7ba3e4c7205d3254e67946baf2 |