p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!5186 Add note of limitation for prarmeters of uniform 

Merge pull request !5186 from peixu_ren/custom_pp_ops
This commit is contained in:
mindspore-ci-bot 2020-08-26 08:37:03 +08:00 committed by Gitee
parent b8da525fb1 5cf472cd39
commit 71f23bdbeb
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mindspore/nn/probability/README.md
View File

@ -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. - Context: context managers for models and layers.
**Layer 3: Toolbox provides a set of BNN tools for some specific applications** **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. - 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") ![Structure of MDP](https://images.gitee.com/uploads/images/2020/0820/115117_2a20da64_7825995.png "MDP.png")

3
mindspore/ops/composite/random_ops.py
View File

@ -96,6 +96,9 @@ def uniform(shape, a, b, seed=0, dtype=mstype.float32):
""" """
Generates random numbers according to the Uniform random number distribution. 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: Args:
shape (tuple): The shape of random tensor to be generated. shape (tuple): The shape of random tensor to be generated.
a (Tensor): The a distribution parameter. a (Tensor): The a distribution parameter.