search

chr5tphr / zennit

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
Other
183 stars 33 forks source link

Canonizers: BatchNorm loses bias relevance #193

Open chr5tphr opened 11 months ago

chr5tphr commented 11 months ago

With the implementation of #185 allowing for gradient computation wrt. the parameters given an attribution with canonizers, the BatchNorms seem to be leaking attribution even with zero_params='bias' on ResNet18.