mindspore.ops.ApplyAdagradV2
- class mindspore.ops.ApplyAdagradV2(epsilon, update_slots=True)[source]
Updates relevant entries according to the adagradv2 scheme.
\[\begin{split}\begin{array}{ll} \\ accum += grad * grad \\ var -= lr * grad * \frac{1}{\sqrt{accum} + \epsilon} \end{array}\end{split}\]where \(\epsilon\) represents epsilon.
Inputs of var, accum and grad comply with the implicit type conversion rules to make the data types consistent. If they have different data types, the lower priority data type will be converted to the relatively highest priority data type.
Note
The difference is that ApplyAdagradV2 has one more small constant value \(\epsilon\) than ApplyAdagrad.
- Parameters
- Inputs:
var (Parameter) - Variable to be updated. With float16 or float32 data type. The shape is \((N, *)\) where \(*\) means, any number of additional dimensions.
accum (Parameter) - Accumulation to be updated. The shape must be the same as var.
lr (Union[Number, Tensor]) - The learning rate value, must be a float number or a scalar tensor with float16 or float32 data type.
grad (Tensor) - A tensor for gradient. The shape must be the same as var.
- Outputs:
Tuple of 2 Tensors, the updated parameters.
var (Tensor) - The same shape and data type as var.
accum (Tensor) - The same shape and data type as accum.
- Raises
- Supported Platforms:
Ascend
GPU
CPU
Examples
>>> import mindspore >>> import numpy as np >>> from mindspore import Tensor, nn, ops, Parameter >>> class Net(nn.Cell): ... def __init__(self): ... super(Net, self).__init__() ... self.apply_adagrad_v2 = ops.ApplyAdagradV2(epsilon=1e-6) ... self.var = Parameter(Tensor(np.array([[0.6, 0.4], ... [0.1, 0.5]]).astype(np.float32)), name="var") ... self.accum = Parameter(Tensor(np.array([[0.6, 0.5], ... [0.2, 0.6]]).astype(np.float32)), name="accum") ... def construct(self, lr, grad): ... out = self.apply_adagrad_v2(self.var, self.accum, lr, grad) ... return out ... >>> net = Net() >>> lr = Tensor(0.001, mindspore.float32) >>> grad = Tensor(np.array([[0.3, 0.7], [0.1, 0.8]]).astype(np.float32)) >>> output = net(lr, grad) >>> print(output) (Tensor(shape=[2, 2], dtype=Float32, value= [[ 5.99638879e-01, 3.99296492e-01], [ 9.97817814e-02, 4.99281585e-01]]), Tensor(shape=[2, 2], dtype=Float32, value= [[ 6.90000057e-01, 9.90000010e-01], [ 2.10000008e-01, 1.24000001e+00]]))