mindspore.ops.random_categorical
- mindspore.ops.random_categorical(logits, num_sample, seed=0, dtype=mstype.int64)[source]
Generates random samples from a given categorical distribution tensor.
- Parameters
logits (Tensor) – The input tensor. 2-D Tensor with shape \((batch\_size, num\_classes)\).
num_sample (int) – Number of sample to be drawn. Only constant values is allowed.
seed (int) – Random seed. Only constant values is allowed. Default: 0.
dtype (mindspore.dtype) – The type of output. Its value must be one of mindspore.int16, mindspore.int32 and mindspore.int64. Default: mindspore.int64.
- Returns
Tensor, The output Tensor with shape \((batch\_size, num\_samples)\).
- Raises
- Supported Platforms:
Ascend
GPU
CPU
Examples
>>> from mindspore import ops >>> from mindspore import Tensor >>> import mindspore.common.dtype as mstype >>> import numpy as np >>> logits = Tensor(np.random.random((10, 5)).astype(np.float32), mstype.float32) >>> net = ops.random_categorical(logits, 8) >>> result = net.shape >>> print(result) (10, 8)