Replication Package for "Why Do Deep Learning Projects Differ in Compatible Framework Versions? An Exploratory Study"

This dataset contains scripts and data used to generate relevant results for this paper. Detailed information are described in README.md. 

code

This folder contains all the scripts used for the experiment. The upgrade.py and downgrade.py are used to perform upgrade and downgrade runs. The pairing.py is used to generate the DFVC pairs. The main.py is used to identify root causes of DFVC pairs.

result

This folder contains all the results of the experiments, including the runtime output (e.g., a_1.0.0.txt), the runtime environment (e.g., condalist_1.0.0.txt), and the project's runtime commands (e.g., pytorch-cifar.xlsx) of all tested 90 PyTorch and 50 TensorFlow projects.

Distribution of dfvc pairs.xlsx

This file includes 6,926 DFVC pairs and their root causes.

Tested framework versions.xlsx

This file includes the framework versions tested and the Python versions that the framework versions are compatible with.

Tested projects.xlsx

This file includes the tested 90 PyTorch projects and 50 TensorFlow projects. We provide the following main information: (a) project name, (b) stars, (c) link, (d) the starting version, (e) python version, (f) incompatible upgrade/downgrade version, and (g) compatible versions.