文档反馈

问题文档片段

问题文档片段包含公式时，显示为空格。

提交类型

issue

有点复杂...

找人问问吧。

请选择提交类型

问题类型

规范和低错类

- 规范和低错类：

- 错别字或拼写错误，标点符号使用错误、公式错误或显示异常。

- 链接错误、空单元格、格式错误。

- 英文中包含中文字符。

- 界面和描述不一致，但不影响操作。

- 表述不通顺，但不影响理解。

- 版本号不匹配：如软件包名称、界面版本号。

易用性

- 易用性：

- 关键步骤错误或缺失，无法指导用户完成任务。

- 缺少主要功能描述、关键词解释、必要前提条件、注意事项等。

- 描述内容存在歧义指代不明、上下文矛盾。

- 逻辑不清晰，该分类、分项、分步骤的没有给出。

正确性

- 正确性：

- 技术原理、功能、支持平台、参数类型、异常报错等描述和软件实现不一致。

- 原理图、架构图等存在错误。

- 命令、命令参数等错误。

- 代码片段错误。

- 命令无法完成对应功能。

- 界面错误，无法指导操作。

- 代码样例运行报错、运行结果不符。

风险提示

- 风险提示：

- 对重要数据或系统存在风险的操作，缺少安全提示。

内容合规

- 内容合规：

- 违反法律法规，涉及政治、领土主权等敏感词。

- 内容侵权。

请选择问题类型

问题描述

点击输入详细问题描述，以帮助我们快速定位问题。

提交

文档反馈

mindspore.ops.ApplyCenteredRMSProp

class mindspore.ops.ApplyCenteredRMSProp(use_locking=False)

Optimizer that implements the centered RMSProp algorithm. Please refer to the usage in source code of nn.RMSProp.

The updating formulas of ApplyCenteredRMSProp algorithm are as follows,

$$\begin{array}{r}\begin{array}{l}\\ g_{t+1}=\rho g_t+(1-\rho )\mathrm{\nabla }{Q}_i(w)\\ s_{t+1}=\rho s_t+(1-\rho )(\mathrm{\nabla }{Q}_i(w){)}^2\\ m_{t+1}=\beta m_t+\frac{\eta }{\sqrt{s_{t+1}-g_{t+1}^2+ϵ}}\mathrm{\nabla }{Q}_i(w)\\ w=w-m_{t+1}\end{array}\end{array}$$

where $w$ represents var, which will be updated. $g_{t+1}$ represents mean_gradient, $g_t$ is the last momentent of $g_{t+1}$. $s_{t+1}$ represents mean_square, $s_t$ is the last momentent of $s_{t+1}$, $m_{t+1}$ represents moment, $m_t$ is the last momentent of $m_{t+1}$. $\rho$ represents decay. $\beta$ is the momentum term, represents momentum. $ϵ$ is a smoothing term to avoid division by zero, represents epsilon. $\eta$ represents learning_rate. $\mathrm{\nabla }{Q}_i(w)$ represents grad.

Note

The difference between ApplyCenteredRMSProp and ApplyRMSProp is that the fromer uses the centered RMSProp algorithm, and the centered RRMSProp algorithm uses an estimate of the centered second moment(i.e., the variance) for normalization, as opposed to regular RMSProp, which uses the (uncentered) second moment. This often helps with training, but is slightly more exapnsive interms of computation and memory.

Warning

In dense implementation of this algorithm, mean_gradient, mean_square, and moment will update even if the grad is zero. But in this sparse implementation, mean_gradient, mean_square, and moment will not update in iterations during which the grad is zero.

Parameters

use_locking (bool) – Whether to enable a lock to protect the variable and accumlation tensors from being updated. Default: False.

Inputs:

• var (Tensor) - Weights to be update.

• mean_gradient (Tensor) - Mean gradients, must have the same type as var.

• mean_square (Tensor) - Mean square gradients, must have the same type as var.

• moment (Tensor) - Delta of var, must have the same type as var.

• grad (Tensor) - Gradient, must have the same type as var.

• learning_rate (Union[Number, Tensor]) - Learning rate. Must be a float number or a scalar tensor with float16 or float32 data type.

• decay (float) - Decay rate.

• momentum (float) - Momentum.

• epsilon (float) - Ridge term.

Outputs:

Tensor, parameters to be update.

Raises

• TypeError – If use_locking is not a bool.

• TypeError – If var, mean_gradient, mean_square, moment or grad is not a Tensor.

• TypeError – If learing_rate is neither a Number nor a Tensor.

• TypeError – If dtype of learing_rate is neither float16 nor float32.

• TypeError – If decay, momentum or epsilon is not a float.

Supported Platforms:

Ascend GPU CPU

Examples

>>> class Net(nn.Cell):
...     def __init__(self):
...         super(Net, self).__init__()
...         self.apply_centerd_rms_prop = ops.ApplyCenteredRMSProp()
...         self.var = Parameter(Tensor(np.ones([2, 2]).astype(np.float32)), name="var")
...
...     def construct(self, mean_grad, mean_square, moment, grad, decay, momentum, epsilon, lr):
...         out = self.apply_centerd_rms_prop(self.var, mean_grad, mean_square, moment, grad,
...                                           lr, decay, momentum, epsilon)
...         return out
...
>>> net = Net()
>>> mean_grad = Tensor(np.ones([2, 2]).astype(np.float32))
>>> mean_square = Tensor(np.ones([2, 2]).astype(np.float32))
>>> moment = Tensor(np.ones([2, 2]).astype(np.float32))
>>> grad = Tensor(np.ones([2, 2]).astype(np.float32))
>>> output = net(mean_grad, mean_square, moment, grad, 0.0, 1e-10, 0.001, 0.01)
>>> print(net.var.asnumpy())
[[0.68377227  0.68377227]
 [0.68377227  0.68377227]]