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.int32)))
>>> print(output1)
[0 0 3]
>>> print(output2)
[[0.75] [0.75] [0.75] [0.75] [0.75]]
>>> print(output3)
[0.75 0.75 0.75]