interpretml / interpret

Fit interpretable models. Explain blackbox machine learning.
https://interpret.ml/docs
MIT License
6.04k stars 714 forks source link

How can I interpret a fully connected nerual network? #504

Open farukalamai opened 3 months ago

farukalamai commented 3 months ago

Here is my model summary,

Sequential( (0): Linear(in_features=49, out_features=64, bias=True) (1): ReLU() (2): Linear(in_features=64, out_features=256, bias=True) (3): ReLU() (4): Linear(in_features=256, out_features=1024, bias=True) (5): ReLU() (6): Linear(in_features=1024, out_features=256, bias=True) (7): ReLU() (8): Linear(in_features=256, out_features=64, bias=True) (9): ReLU() (10): Linear(in_features=64, out_features=49, bias=True) (11): Sigmoid() )