climb.tool.impl.data_suite.third_party.uq360.models package¶
Subpackages¶
- climb.tool.impl.data_suite.third_party.uq360.models.bayesian_neural_networks package
- Subpackages
- Submodules
- climb.tool.impl.data_suite.third_party.uq360.models.bayesian_neural_networks.layer_utils module
- climb.tool.impl.data_suite.third_party.uq360.models.bayesian_neural_networks.layers module
- climb.tool.impl.data_suite.third_party.uq360.models.bayesian_neural_networks.misc module
- Module contents
- climb.tool.impl.data_suite.third_party.uq360.models.noise_models package
- Submodules
- climb.tool.impl.data_suite.third_party.uq360.models.noise_models.heteroscedastic_noise_models module
- climb.tool.impl.data_suite.third_party.uq360.models.noise_models.homoscedastic_noise_models module
- climb.tool.impl.data_suite.third_party.uq360.models.noise_models.noisemodel module
- Module contents
Submodules¶
climb.tool.impl.data_suite.third_party.uq360.models.heteroscedastic_mlp module¶
- class climb.tool.impl.data_suite.third_party.uq360.models.heteroscedastic_mlp.GaussianNoiseMLPNet(num_features, num_outputs, num_hidden)[source]¶
Bases:
Module- forward(x)[source]¶
Define the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.