DeepDIVA

A Highly-Functional Python Framework for Reproducible Experiments

Try it on Github

Deep-learning
Out-of-the-Box

PyTorch integration for common deep learning scenarios

Automatic
Hyper-parameter
Optimization

Smarter than grid-search with SigOpt

DeepDIVA as a
Web Service

Run your own, and reproduce the experiments of others in the cloud

Data
Visualization

An image is worth a thousand lines of logs

New Dataset Support

Scripts to prepare your datasets faster

Comparing Methods

How effective are your changes?

Internal Inspection

Find out what happens inside your network

Working on 2D Data

Understand your networks better on toy-problems

DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments

Abstract.We introduce DeepDIVA: an infrastructure designed to enable and intuitive setup of reproducible experiments with a range of useful analysis functionality. Reproducing scientific can be a frustrating experience, not only in document image analysis but in machine learning in general. Using DeepDIVA a researcher can either reproduce a given with a very limited amount of information or share their own experiments with others. Moreover, the framework a large range of functions, such as boilerplate code, keeping track of experiments, hyper-parameter optimization, and visualization of data and results. To demonstrate the effectiveness of this framework, this paper presents case studies in the area of handwritten document analysis where researchers benefit from the integrated functionality. DeepDIVA is implemented in Python and uses the deep learning framework PyTorch. It is completely open source, and accessible as Web Service through DIVAServices.

Paper onarXiv.org.

Improving Reproducible Deep Learning Workflows with DeepDIVA

Abstract.The field of deep learning is experiencing a trend towards producing reproducible research. Nevertheless, it is still often a frustrating experience to reproduce scientific results. This is especially true in the machine learning community, where it is considered acceptable to have black boxes in your experiments. We present DeepDIVA, a framework designed to facilitate easy experimentation and their reproduction. This framework allows researchers to share their experiments with others, while providing functionality that allows for easy experimentation, such as: boilerplate code, experiment management, hyper-parameter optimization, verification of data integrity and visualization of data and results. Additionally, the code of DeepDIVA is well-documented and supported by several tutorials that allow a new user to quickly familiarize themselves with the framework.