Official TensorFlow implementation for Feature Map Retargeting to Classify Biomedical Journal Figures . The code has been implemented and tested on the Ubuntu operating system only.
First, install the CUDA Toolkit and the cuDNN library matching the version of your Ubuntu operating system. Installation of the Anaconda Python Distribution is required as well. We recommend installing CUDA10.1. Then find the TensorFlow version compatible with your CUDA version here.
Then, run the following commands:
conda env create -f config/enviroment.yml
conda activate Retarget
conda install -c conda-forge cudatoolkit=10.1 cudnn=7.6.0
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CONDA_PREFIX/lib/
pip install --upgrade pip
pip install tensorflow-gpu==2.2.0
Visit the ImageCLEF2013, ImageCLEF2015, and ImageCLEF2016 websites to register and download the datasets.
The datasets follow the directory structure below:
├── datasets
│ ├── ImageCLEF13
│ | ├── train
│ | | ├── category 1
│ | | ├── category 2
│ | ├── test
│ ├── ImageCLEF15
│ ├── ImageCLEF16
python train.py
python test.py
If you found this work helpful for your research, please consider citing us.
@inproceedings{singh2020feature,
title={Feature Map Retargeting to Classify Biomedical Journal Figures},
author={Singh, Vinit Veerendraveer and Kambhamettu, Chandra},
booktitle={International Symposium on Visual Computing},
pages={728--741},
year={2020},
organization={Springer}
}