Refactor the input to static analysis engine to avoid directly taking Pytorch models

dependable-ai / nn-dependability-kit

Toolbox for software dependability engineering of artificial neural networks

GNU Affero General Public License v3.0

34 stars 9 forks source link

Refactor the input to static analysis engine to avoid directly taking Pytorch models #18

Closed chengchihhong closed 5 years ago

chengchihhong commented 5 years ago

By having an intermediate model, one can unify the input model of tensorflow and the input model of pytorch, such that the parameter extraction process will not be framework specific.