Published July 15, 2020 | Version v1
Software Open

Deeplabv3+ models for the aradeepopsis pipeline

  • 1. Gregor Mendel Institute of Molecular Plant Biology GmbH
  • 2. Gregor Mendel Institute of Molecular Plant Biology GmbH; Ludwig-Maximilians-Universitat Munchen

Description

Transfer learning of the DeepLabv3+ model (xception backbone) for use with aradeepopsis in single- or multi-scale mode.

1_class corresponds to model A; 2_class to model B and 3_class to model C as described here

The datasets used for training are available at https://doi.org/10.5281/zenodo.3946393 and the code used for transfer learning is available on GitHub

Files

Files (1.0 GB)

Name Size Download all
md5:52eb51e5b62199d0e8167d28f171c990
169.1 MB Download
md5:bfe74d476b5f9dee87c8af9503d2d2fe
165.7 MB Download
md5:cecd65a73c3090d3b4bcd75c6b88f416
169.1 MB Download
md5:add1e6dc8df75261cd0cefc9d8c398dc
165.7 MB Download
md5:e3c87022467c568bf35b50c2295b26ba
169.1 MB Download
md5:f308e6a748ee587af1eb31ce968cf735
165.7 MB Download

Additional details

Related works

Is supplement to
Software: 10.5281/zenodo.3946321 (DOI)

Funding

FEAR-SAP – Function and Evolution of Attack and Response Strategies during Allelopathy in Plants 716823
European Commission

References

  • Hüther, P.; Schandry, N.; Jandrasits, K.; Bezrukov, I.; Becker, C. aradeepopsis: From images to phenotypic traits using deep transfer learning. bioRxiv, 2020, 2020.04.01.018192.
  • Chen, L.-C.; Zhu, Y.; Papandreou, G.; Schroff, F.; Adam, H. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. arXiv [cs.CV], 2018.