mindspore.ops.ApplyRMSProp
- class mindspore.ops.ApplyRMSProp(use_locking=False)[source]
Optimizer that implements the Root Mean Square prop(RMSProp) algorithm. Please refer to the usage in source code of
mindspore.nn.RMSProp
.The updating formulas of ApplyRMSProp algorithm are as follows,
\[\begin{split}\begin{array}{ll} \\ s_{t+1} = \rho s_{t} + (1 - \rho)(\nabla Q_{i}(w))^2 \\ m_{t+1} = \beta m_{t} + \frac{\eta} {\sqrt{s_{t+1} + \epsilon}} \nabla Q_{i}(w) \\ w = w - m_{t+1} \end{array}\end{split}\]where \(w\) represents var, which will be updated. \(s_{t+1}\) represents mean_square, \(s_{t}\) is the last moment of \(s_{t+1}\), \(m_{t+1}\) represents moment, \(m_{t}\) is the last moment of \(m_{t+1}\). \(\rho\) represents decay. \(\beta\) is the momentum term, represents momentum. \(\epsilon\) is a smoothing term to avoid division by zero, represents epsilon. \(\eta\) represents learning_rate. \(\nabla Q_{i}(w)\) represents grad.
Warning
Note that in dense implementation of this algorithm, "mean_square" and "moment" will update even if "grad" is 0, but in this sparse implementation, "mean_square" and "moment" will not update in iterations during which "grad" is 0.
- Parameters
use_locking (bool) – Whether to enable a lock to protect the variable and accumulation tensors from being updated. Default:
False
.
- Inputs:
var (Parameter) - Weights to be updated.
mean_square (Tensor) - Mean square gradients, must be the same type as var.
moment (Tensor) - Delta of var, must be 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.
grad (Tensor) - Gradient, must be the same type as var.
decay (float) - Decay rate. Only constant value is allowed.
momentum (float) - Momentum. Only constant value is allowed.
epsilon (float) - Ridge term. Only constant value is allowed.
- Outputs:
Tensor, parameters to be updated.
- Raises
TypeError – If use_locking is not a bool.
TypeError – If var, mean_square, moment or decay is not a Tensor.
TypeError – If learning_rate is neither a Number nor a Tensor.
TypeError – If dtype of decay, momentum or epsilon is not float.
TypeError – If dtype of learning_rate is neither float16 nor float32.
ValueError – If decay, momentum or epsilon is not a constant value.
- Supported Platforms:
Ascend
GPU
CPU
Examples
>>> import numpy as np >>> from mindspore import Tensor, nn, ops, Parameter >>> class Net(nn.Cell): ... def __init__(self): ... super(Net, self).__init__() ... self.apply_rms_prop = ops.ApplyRMSProp() ... self.var = Parameter(Tensor(np.ones([2, 2]).astype(np.float32)), name="var") ... ... def construct(self, mean_square, moment, grad, decay, momentum, epsilon, lr): ... out = self.apply_rms_prop(self.var, mean_square, moment, lr, grad, decay, momentum, epsilon) ... return out ... >>> net = Net() >>> 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_square, moment, grad, 0.0, 1e-10, 0.001, 0.01) >>> print(net.var.asnumpy()) [[0.990005 0.990005] [0.990005 0.990005]]