Shortcuts

Metrics

Classification & Segmentation

Accuracy

tllib.utils.metric.accuracy(output, target, topk=(1, ))[source]

Computes the accuracy over the k top predictions for the specified values of k

Parameters
  • output (tensor) – Classification outputs, \((N, C)\) where C = number of classes

  • target (tensor) – \((N)\) where each value is \(0 \leq \text{targets}[i] \leq C-1\)

  • topk (sequence[int]) – A list of top-N number.

Returns

Top-N accuracies (N \(\in\) topK).

ConfusionMatrix

class tllib.utils.metric.ConfusionMatrix(num_classes)[source]
compute()[source]

compute global accuracy, per-class accuracy and per-class IoU

format(classes)[source]

Get the accuracy and IoU for each class in the table format

update(target, output)[source]

Update confusion matrix.

Parameters
  • target – ground truth

  • output – predictions of models

Shape:
  • target: \((minibatch, C)\) where C means the number of classes.

  • output: \((minibatch, C)\) where C means the number of classes.

Docs

Access comprehensive documentation for Transfer Learning Library

View Docs

Tutorials

Get started for Transfer Learning Library

Get Started

Paper List

Get started for transfer learning

View Resources