提交 5cf472cd 编写于 作者: P peixu_ren

Add note of limitation for prarmeters of uniform

上级 2b23de61
无相关合并请求
......@@ -32,7 +32,7 @@ The objective of MDP is to integrate deep learning with Bayesian learning. On th
- Context: context managers for models and layers.
**Layer 3: Toolbox provides a set of BNN tools for some specific applications**
- Uncertainty Estimation([mindspore.nn.probability.toolbox.uncertainty_evaluate](https://gitee.com/mindspore/mindspore/tree/master/mindspore/nn/probability/toolbox/uncertainty_evaluate.py)): Interfaces to estimate epistemic uncertainty and aleatoric uncertainty.
- Uncertainty Estimation([mindspore.nn.probability.toolbox.uncertainty_evaluation](https://gitee.com/mindspore/mindspore/tree/master/mindspore/nn/probability/toolbox/uncertainty_evaluation.py)): Interfaces to estimate epistemic uncertainty and aleatoric uncertainty.
- OoD detection: Interfaces to detect out of distribution samples.
![Structure of MDP](https://images.gitee.com/uploads/images/2020/0820/115117_2a20da64_7825995.png "MDP.png")
......
......@@ -96,6 +96,9 @@ def uniform(shape, a, b, seed=0, dtype=mstype.float32):
"""
Generates random numbers according to the Uniform random number distribution.
Note:
The number in tensor a should be strictly less than b at any position after broadcasting.
Args:
shape (tuple): The shape of random tensor to be generated.
a (Tensor): The a distribution parameter.
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部