mindspore.nn.SampledSoftmaxLoss

class mindspore.nn.SampledSoftmaxLoss(num_sampled, num_classes, num_true=1, sampled_values=None, remove_accidental_hits=True, seed=0, reduction='none')[source]

Computes the sampled softmax training loss.

Parameters

  • num_sampled (int) – The number of classes to randomly sample per batch.

  • num_classes (int) – The number of possible classes.

  • num_true (int) – The number of target classes per training example.

  • sampled_values (Union[list, tuple]) – List or tuple of (sampled_candidates, true_expected_count, sampled_expected_count) returned by a *CandidateSampler function. Default to None, UniformCandidateSampler is applied.

  • remove_accidental_hits (bool) – Whether to remove “accidental hits” where a sampled class equals one of the target classes. Default is True.

  • seed (int) – Random seed for candidate sampling. Default: 0

  • reduction (str) – Type of reduction to be applied to loss. The optional values are “mean”, “sum”, and “none”. If “none”, do not perform reduction. Default: “none”.

Inputs:

  • weights (Tensor) - Tensor of shape (C, dim).

  • bias (Tensor) - Tensor of shape (C). The class biases.

  • labels (Tensor) - Tensor of shape (N, num_true), type int64, int32. The target classes.

  • inputs (Tensor) - Tensor of shape (N, dim). The forward activations of the input network.

Outputs:

Tensor, a tensor of shape (N) with the per-example sampled softmax losses.

Raises

  • TypeError – If sampled_values is not a list or tuple.

  • TypeError – If dtype of labels is neither int32 not int64.

  • ValueError – If reduction is not one of ‘none’, ‘mean’, ‘sum’.

  • ValueError – If num_sampled or num_true is great than num_classes.

  • ValueError – If length of sampled_values is not equal to 3.

Supported Platforms:

GPU

Examples

>>> mindspore.set_seed(1)
>>> loss = nn.SampledSoftmaxLoss(num_sampled=4, num_classes=7, num_true=1)
>>> weights = Tensor(np.random.randint(0, 9, [7, 10]), mindspore.float32)
>>> biases = Tensor(np.random.randint(0, 9, [7]), mindspore.float32)
>>> labels = Tensor([0, 1, 2])
>>> inputs = Tensor(np.random.randint(0, 9, [3, 10]), mindspore.float32)
>>> output = loss(weights, biases, labels, inputs)
>>> print(output)
[4.6051701e+01 1.4000047e+01 6.1989022e-06]