torchood 0.0.1

implement of local laplace filter algorithm

[torchood]: pytorch implementation for universal out of distribution methods

pip install torchood

Support Methods

Support Methods	Source
Robust Classification with Convolutional Prototype Learning (Prototype Networks)	CVPR 2018: Rbust classification with convolutional prototype learning
Predictive Uncertainty Estimation via Prior Networks(Prior Networks)	NeurIPS 2018: Predictive Uncertainty Estimation via Prior Networks
Evidential Deep Learning to Quantify Classification Uncertainty (EDL)	NeurIPS 2018: Evidential Deep Learning to Quantify Classification Uncertainty
Posterior Network (PostNet)	NeurIPS 2020: Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
Evidential Neural Network (ENN)	NeurIPS 2018: Evidential Deep Learning to Quantify Classification Uncertainty
Evidence Reconciled Neural Network(ERNN)	MICCAI 2023: Evidence Reconciled Neural Network for Out-of-Distribution Detection in Medical Images
Redundancy Removing Evidential Neural Network(R2ENN)	-

---

Usage

pip install torchood

import torchood

class UserDefineModel(nn.Module):
    ...

classifier = UserDefineModel(...)
classifier = torchood.EvidenceNeuralNetwork(classifier)

Train

for data, label in train_loader:
    # transform data & label to correct device
    # ...

    _, evidence, _ = classifier(data)
    loss = classifier.criterion(evidence, label)

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

Infer

prob, uncertainty = classifier.predict(inputs)