mindspore.ops.UniformCandidateSampler

class mindspore.ops.UniformCandidateSampler(num_true, num_sampled, unique, range_max, seed=0, remove_accidental_hits=False)[source]

Uniform candidate sampler.

This function samples a set of classes(sampled_candidates) from [0, range_max-1] based on uniform distribution.

Refer to mindspore.ops.uniform_candidate_sampler() for more detail.

Supported Platforms:: Ascend GPU CPU

Examples

>>> sampler = ops.UniformCandidateSampler(1, 3, False, 4, 1)
>>> output1, output2, output3 = sampler(Tensor(np.array([[1], [3], [4], [6], [3]], dtype=np.int64)))
>>> print(output1.shape)
(3,)
>>> print(output2.shape)
(5, 1)
>>> print(output3.shape)
(3,)