DIVA-DAF
Description
A deep learning framework for historical document image analysis.
How to run
Install dependencies
# clone project
git clone https://github.com/DIVA-DIA/unsupervised_learning.git
cd unsupervised_learing
# create conda environment (IMPORTANT: needs Python 3.8+)
conda env create -f conda_env_gpu.yaml
# activate the environment using .autoenv
source .autoenv
# install requirements
pip install -r requirements.txt
Train model with default configuration. Care: you need to change the value of data_dir in config/datamodule/cb55_10_cropped_datamodule.yaml.
# default run based on config/config.yaml
python run.py
# train on CPU
python run.py trainer.gpus=0
# train on GPU
python run.py trainer.gpus=1
Train using GPU
# [default] train on all available GPUs
python run.py trainer.gpus=-1
# train on one GPU
python run.py trainer.gpus=1
# train on two GPUs
python run.py trainer.gpus=2
# train on CPU
python run.py trainer.accelerator=ddp_cpu
Train using CPU for debugging
# train on CPU
python run.py trainer.accelerator=ddp_cpu trainer.precision=32
Train model with chosen experiment configuration from configs/experiment/
python run.py +experiment=experiment_name
You can override any parameter from command line like this
python run.py trainer.max_epochs=20 datamodule.batch_size=64
Setup PyCharm
- Fork this repo
- Clone the repo to your local filesystem (
git clone CLONELINK) - Clone the repo onto your remote machine
- Move into the folder on your remote machine and create the conda environment (conda env create -f conda_env_gpu.yaml)
- Run
source .autoenvin the root folder on your remote machine (activates the environment) - Open the folder in PyCharm (File -> open)
- Add the interpreter (Preferences -> Project -> Python interpreter -> top left gear icon -> add... -> SSH Interpreter) follow the instructions (set the correct mapping to enable deployment)
- Upload the files (deployment)
- Create a wandb account (wandb.ai)
- Log via ssh onto your remote machine
- Go to the root folder of the framework and activate the environment (source .autoenv OR conda activate unsupervised_learning)
- Log into wandb. Execute
wandb loginand follow the instructions - Now you should be able to run the basic experiment from PyCharm
Loading models
You can load the different model parts backbone or header as well as the whole task. To load the backbone or the header you need to add to your experiment config the field path_to_weights. e.g.
model:
header:
path_to_weights: /my/path/to/the/pth/file
To load the whole task you need to provide the path to the whole task to the trainer. This is with the field resume_from_checkpoint. e.g.
trainer:
resume_from_checkpoint: /path/to/.ckpt/file
Freezing model parts
You can freeze both parts of the model (backbone or header) with the freeze flag in the config. E.g. you want to freeze the backbone: In the command line:
python run.py +model.backbone.freeze=True
In the config (e.g. model/backbone/baby_unet_model.yaml):
...
freeze: True
...
CARE: You can not train a model when you do not have trainable parameters (e.g. freezing backbone and header).
Selection in datasets
If you use the selection key you can either use an int, which takes the first n files, or a list of strings to filter the different datasets. In the case you are using a full-page dataset be aware that the selection list is a list of file names without the extension.
Cite us
@misc{vögtlin2022divadaf,
title={DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis},
author={Lars Vögtlin and Paul Maergner and Rolf Ingold},
year={2022},
eprint={2201.08295},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
18 Nov 14, 2022
51 Nov 17, 2022
9 Dec 28, 2022
68 Dec 20, 2022
61 Nov 28, 2022
282 Jan 02, 2023
63 Dec 01, 2022
22 Mar 16, 2022
1 Nov 14, 2021
21 Dec 27, 2022
344 Dec 29, 2022
12 Dec 27, 2022
[email protected]">
1 Nov 01, 2021
16 Jul 11, 2022
1 Oct 13, 2021
370 Dec 27, 2022
50 Oct 08, 2021
46 Dec 17, 2022
187 Jan 04, 2023
10 Nov 02, 2022