Pre-trained PlantCLEF models (from ExpertLifeCLEF 2018)

In order to support research in fine-grained plant classification, we share the pre-trained Inception-v4 and Inception-ResNet-v2 CNN models from our winning submission to the ExpertLifeCLEF 2018 Plant identification task.
We believe the pre-trained models may be a good starting point for the participants of PlantCLEF 2019.

Usage

The models are shared in the form of TensorFlow checkpoints, and can be used directly within the TensorFlow slim framework. Information about the model parameters are in our LifeCLEF 2018 paper (CNN #1 and CNN #4).

Models

[DIR] inception_v4/
[DIR] inception_resnet_v2/  

License

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
I.e.: The models are shared only for non-commercial purposes. If you publish experiments/results based on the models, please attribute us by citing the related paper, Plant recognition by Inception networks with test-time class prior estimation. BibTex:
@InProceedings{sulc2018lifeclef,
  title={Plant recognition by Inception networks with test-time class prior estimation},
  author={Sulc, Milan and Picek, Lukas and Matas, Jiri},
  booktitle= {Working Notes of CLEF 2018 - Conference and Labs of the
		  Evaluation Forum},
  year={2018}
}