Differences with torch.nn.Tanh

torch.nn.Tanh

class torch.nn.Tanh()(input) -> Tensor

For more information, see torch.nn.Tanh.

mindspore.nn.Tanh

class mindspore.nn.Tanh()(x) -> Tensor

For more information, see mindspore.nn.Tanh.

Differences

PyTorch: Compute the hyperbolic tangent function tanh.

MindSpore: MindSpore API implements the same function as PyTorch.

Categories	Subcategories	PyTorch	MindSpore	Difference
Input	Single input	input	x	Same function, different parameter names

Code Example

Compute the tanh function for input x, and MindSpore API function is consistent with PyTorch.

# PyTorch
import numpy as np
import torch
from torch import tensor, nn

m = nn.Tanh()
x_ = np.array([0.7713, 0.0208, 0.6336], dtype=np.float32)
x = tensor(x_)
output = m(x)
print(output.numpy())
# [0.64768475 0.020797   0.56052613]

# MindSpore
import numpy as np
import mindspore
from mindspore import Tensor, nn

m = nn.Tanh()
x_ = np.array([0.7713, 0.0208, 0.6336], dtype=np.float32)
x = Tensor(x_, mindspore.float32)
output = m(x)
print(output)
# [0.64768475 0.020797   0.56052613]