Releases: DIVA-DIA/DeepDIVA
DeepDIVA 1.0
This version of the software has been presented at the 6th Swiss Conference on Data Science (SDS), with the paper "Improving Reproducible Deep Learning Workflows with DeepDIVA".
The current release of DeepDIVA uses PyTorch 1.0 which introduces several API changes compared to the version we were using in the earlier release (PyTorch 0.3). The DeepDIVA codebase has been updated to be compliant with these changes (https://pytorch.org/blog/pytorch-0_4_0-migration-guide/). Additionally, all of the packages have been updated including an update to Python 3.7.
Initial version
This version of the software has been presented at the 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), with the paper "DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments".