mindspore.ops.LogUniformCandidateSampler

class mindspore.ops.LogUniformCandidateSampler(num_true=1, num_sampled=5, unique=True, range_max=5, seed=0)[source]

Generates random labels with a log-uniform distribution for sampled_candidates.

Randomly samples a tensor of sampled classes from the range of integers [0, range_max).

Refer to mindspore.ops.log_uniform_candidate_sampler() for more details.

Parameters

  • num_true (int, optional) – The number of target classes per training example. Default: 1 .

  • num_sampled (int, optional) – The number of classes to randomly sample. Default: 5 .

  • unique (bool, optional) – Determines whether sample with rejection. If unique is True , all sampled classes in a batch are unique. Default: True .

  • range_max (int, optional) – The number of possible classes. When unique is True , range_max must be greater than or equal to num_sampled. Default: 5 .

  • seed (int, optional) – Random seed, must be non-negative. Default: 0 .

Inputs:

  • true_classes (Tensor) - The target classes. With data type of int64 and shape \((batch\_size, num\_true)\) .

Outputs:

Tuple of 3 Tensors.

  • sampled_candidates (Tensor) - A Tensor with shape \((num\_sampled,)\) and the same type as true_classes.

  • true_expected_count (Tensor) - A Tensor with the same shape as true_classes and type float32.

  • sampled_expected_count (Tensor) - A Tensor with the same shape as sampled_candidates and type float32.

Supported Platforms:

Ascend CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> sampler = ops.LogUniformCandidateSampler(2, 5, True, 5)
>>> output1, output2, output3 = sampler(Tensor(np.array([[1, 7], [0, 4], [3, 3]])))
>>> print(output1, output2, output3)
[3 2 0 4 1]
[[0.92312991 0.49336370]
 [0.99248987 0.65806371]
 [0.73553443 0.73553443]]
[0.73553443 0.82625800 0.99248987 0.65806371 0.92312991]