Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
Project description
QuickTune (WIP)
Quick-Tune: Quickly Learning Which Pre Trained Model to Fine Tune and How ICLR2024
This repo contains the code for running experiments with QuickTune
Run QuickTune
Prepare Environment
To install QuickTune, you can simply use pip
:
pip install quicktune
Download the QuickTune Meta-Dataset:
wget https://rewind.tf.uni-freiburg.de/index.php/s/oMxC5sfrkA53ESo/download/qt_metadataset.zip
unzip qt_metadataset.zip
Run on Custom Dataset
The custom dataset must be in Pytorch's ImageFolder format, e.g. download the Imagenette dataset:
wget https://s3.amazonaws.com/fast-ai-imageclas/imagenette2-320.tgz
tar -xvzf imagenette2-320.tgz
Modify the quicktuning script in the examples folder to your needs.
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
quicktune-0.0.5.dev3.tar.gz
(81.7 kB
view hashes)
Built Distribution
Close
Hashes for quicktune-0.0.5.dev3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | bb26baa79ac08d3c402c2528666b8cf41114491352bae132c0389a14182170b9 |
|
MD5 | 1d5d42ec5b02e567c0bcff2aa46f0127 |
|
BLAKE2b-256 | ef1330f681ac8c4ac6ae0aecbacaf06ef4efc863e0a80093d406e16410a0d33b |