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。

文档反馈

mindspore.nn.RMSProp

class mindspore.nn.RMSProp(*args, **kwargs)[source]

Implements Root Mean Squared Propagation (RMSProp) algorithm.

Update params according to the RMSProp algorithm. The 29th of the original presentation slide [http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf] proposes RMSProp. The equation is as follows:

s_{t + 1} = ρ s_{t} + (1 - ρ) (\nabla Q_{i} (w))^{2}

m_{t + 1} = β m_{t} + \frac{η}{\sqrt{s_{t + 1} + ϵ}} \nabla Q_{i} (w)

w = w - m_{t + 1}

The first equation calculates moving average of the squared gradient for each weight. Then dividing the gradient by $\sqrt{m s_{t + 1} + ϵ}$ .

If centered is True:

g_{t + 1} = ρ g_{t} + (1 - ρ) \nabla Q_{i} (w)

s_{t + 1} = ρ s_{t} + (1 - ρ) (\nabla Q_{i} (w))^{2}

m_{t + 1} = β m_{t} + \frac{η}{\sqrt{s_{t + 1} - g_{t + 1}^{2} + ϵ}} \nabla Q_{i} (w)

w = w - m_{t + 1}

where $w$ represents params, which will be updated. $g_{t + 1}$ is mean gradients. $s_{t + 1}$ is the mean square gradients. $m_{t + 1}$ is moment, the delta of w. $ρ$ represents decay. $β$ is the momentum term, represents momentum. $ϵ$ is a smoothing term to avoid division by zero, represents epsilon. $η$ is learning rate, represents learning_rate. $\nabla Q_{i} (w)$ is gradients, represents gradients. $t$ represents the current step.

Note

If parameters are not grouped, the weight_decay in optimizer will be applied on the network parameters without ‘beta’ or ‘gamma’ in their names. Users can group parameters to change the strategy of decaying weight. When parameters are grouped, each group can set weight_decay, if not, the weight_decay in optimizer will be applied.

Parameters

params (Union[list[Parameter], list[dict]]) –
Must be list of Parameter or list of dict. When the params is a list of dict, the string “params”, “lr”, “weight_decay”, “grad_centralization” and “order_params” are the keys can be parsed.
- params: Required. Parameters in current group. The value must be a list of Parameter.
- lr: Optional. If “lr” in the keys, the value of corresponding learning rate will be used. If not, the learning_rate in optimizer will be used. Fixed and dynamic learning rate are supported.
- weight_decay: Optional. If “weight_decay” in the keys, the value of corresponding weight decay will be used. If not, the weight_decay in the optimizer will be used.
- grad_centralization: Optional. Must be Boolean. If “grad_centralization” is in the keys, the set value will be used. If not, the grad_centralization is False by default. This configuration only works on the convolution layer.
- order_params: Optional. When parameters are grouped, this usually is used to maintain the order of parameters that appeared in the network to improve performance. The value should be parameters whose order will be followed in optimizer. If order_params in the keys, other keys will be ignored and the element of ‘order_params’ must be in one group of params.
learning_rate (Union[float, int, Tensor, Iterable, LearningRateSchedule]) –
Default: 0.1.
- float: The fixed learning rate value. Must be equal to or greater than 0.
- int: The fixed learning rate value. Must be equal to or greater than 0. It will be converted to float.
- Tensor: Its value should be a scalar or a 1-D vector. For scalar, fixed learning rate will be applied. For vector, learning rate is dynamic, then the i-th step will take the i-th value as the learning rate.
- Iterable: Learning rate is dynamic. The i-th step will take the i-th value as the learning rate.
- LearningRateSchedule: Learning rate is dynamic. During training, the optimizer calls the instance of LearningRateSchedule with step as the input to get the learning rate of the current step.
decay (float) – Decay rate. Should be equal to or greater than 0. Default: 0.9.
momentum (float) – Hyperparameter of type float, means momentum for the moving average. Should be equal to or greater than 0. Default: 0.0.
epsilon (float) – Term added to the denominator to improve numerical stability. Should be greater than 0. Default: 1e-10.
use_locking (bool) – Whether to enable a lock to protect the updating process of variable tensors. Default: False.
centered (bool) – If True, gradients are normalized by the estimated variance of the gradient. Default: False.
loss_scale (float) – A floating point value for the loss scale. Should be greater than 0. In general, use the default value. Only when FixedLossScaleManager is used for training and the drop_overflow_update in FixedLossScaleManager is set to False, then this value needs to be the same as the loss_scale in FixedLossScaleManager. Refer to class mindspore.FixedLossScaleManager for more details. Default: 1.0.
weight_decay (Union[float, int]) – Weight decay (L2 penalty). Should be equal to or greater than 0. Default: 0.0.

Inputs:

gradients (tuple[Tensor]) - The gradients of params, the shape is the same as params.

Outputs:

Tensor[bool], the value is True.

Raises

TypeError – If learning_rate is not one of int, float, Tensor, Iterable, LearningRateSchedule.
TypeError – If decay, momentum, epsilon or loss_scale is not a float.
TypeError – If element of parameters is neither Parameter nor dict.
TypeError – If weight_decay is neither float nor int.
TypeError – If use_locking or centered is not a bool.
ValueError – If epsilon is less than or equal to 0.
ValueError – If decay or momentum is less than 0.

Supported Platforms:: Ascend GPU CPU

Examples

>>> from mindspore import nn, Model
>>>
>>> net = Net()
>>> #1) All parameters use the same learning rate and weight decay
>>> optim = nn.RMSProp(params=net.trainable_params(), learning_rate=0.1)
>>>
>>> #2) Use parameter groups and set different values
>>> conv_params = list(filter(lambda x: 'conv' in x.name, net.trainable_params()))
>>> no_conv_params = list(filter(lambda x: 'conv' not in x.name, net.trainable_params()))
>>> group_params = [{'params': conv_params, 'weight_decay': 0.01, 'grad_centralization':True},
...                 {'params': no_conv_params, 'lr': 0.01},
...                 {'order_params': net.trainable_params()}]
>>> optim = nn.RMSProp(group_params, learning_rate=0.1, weight_decay=0.0)
>>> # The conv_params's parameters will use default learning rate of 0.1 and weight decay of 0.01 and grad
>>> # centralization of True.
>>> # The no_conv_params's parameters will use learning rate of 0.01 and default weight decay of 0.0 and grad
>>> # centralization of False.
>>> # The final parameters order in which the optimizer will be followed is the value of 'order_params'.
>>>
>>> loss = nn.SoftmaxCrossEntropyWithLogits()
>>> model = Model(net, loss_fn=loss, optimizer=optim)