Accuracy

class paddle.metric. Accuracy ( topk: Sequence[int] = (1,), name: str | None = None, *args: Any, **kwargs: Any ) [source]

Encapsulates accuracy metric logic.

Parameters

  • topk (list[int]|tuple[int]) – Number of top elements to look at for computing accuracy. Default is (1,).

  • name (str|None, optional) – String name of the metric instance. Default is acc.

Examples

>>> import numpy as np
>>> import paddle

>>> x = paddle.to_tensor(np.array([
...     [0.1, 0.2, 0.3, 0.4],
...     [0.1, 0.4, 0.3, 0.2],
...     [0.1, 0.2, 0.4, 0.3],
...     [0.1, 0.2, 0.3, 0.4]]))
>>> y = paddle.to_tensor(np.array([[0], [1], [2], [3]]))

>>> m = paddle.metric.Accuracy()
>>> correct = m.compute(x, y)
>>> m.update(correct)
>>> res = m.accumulate()
>>> print(res)
0.75

>>> 
>>> import paddle
>>> from paddle.static import InputSpec
>>> import paddle.vision.transforms as T
>>> from paddle.vision.datasets import MNIST

>>> input = InputSpec([None, 1, 28, 28], 'float32', 'image')
>>> label = InputSpec([None, 1], 'int64', 'label')
>>> transform = T.Compose([T.Transpose(), T.Normalize([127.5], [127.5])])
>>> train_dataset = MNIST(mode='train', transform=transform)

>>> model = paddle.Model(paddle.vision.models.LeNet(), input, label)
>>> optim = paddle.optimizer.Adam(
...     learning_rate=0.001, parameters=model.parameters())
>>> model.prepare(
...     optim,
...     loss=paddle.nn.CrossEntropyLoss(),
...     metrics=paddle.metric.Accuracy())
...
>>> model.fit(train_dataset, batch_size=64)
compute ( pred: Tensor, label: Tensor, *args: Any ) → Tensor

compute

Compute the top-k (maximum value in topk) indices.

Parameters

  • pred (Tensor) – The predicted value is a Tensor with dtype float32 or float64. Shape is [batch_size, d0, …, dN].

  • label (Tensor) – The ground truth value is Tensor with dtype int64. Shape is [batch_size, d0, …, 1], or [batch_size, d0, …, num_classes] in one hot representation.

Returns

Correct mask, a tensor with shape [batch_size, d0, …, topk].

Return type

Tensor

update ( correct: Tensor, *args: Any ) → Tensor

update

Update the metrics states (correct count and total count), in order to calculate cumulative accuracy of all instances. This function also returns the accuracy of current step.

Parameters

correct – Correct mask, a tensor with shape [batch_size, d0, …, topk].

Returns

the accuracy of current step.

Return type

Tensor

reset ( ) → None

reset

Resets all of the metric state.

accumulate ( ) → list[float]

accumulate

Computes and returns the accumulated metric.

name ( ) → list[str]

name

Return name of metric instance.

Used in the guide/tutorials