比较与torch.nn.BatchNorm1d的功能差异

class torch.nn.BatchNorm1d(
    num_features,
    eps=1e-05,
    momentum=0.1,
    affine=True,
    track_running_stats=True
)(input) -> Tensor

class mindspore.nn.BatchNorm1d(
    num_features,
    eps=1e-5,
    momentum=0.9,
    affine=True,
    gamma_init='ones',
    beta_init='zeros',
    moving_mean_init='zeros',
    moving_var_init='ones',
    use_batch_statistics=None,
    data_format='NCHW'
)(x) -> Tensor

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

net = nn.BatchNorm1d(4, affine=False, momentum=0.1)
x = tensor(np.array([[0.7, 0.5, 0.5, 0.6], [0.5, 0.4, 0.6, 0.9]]).astype(np.float32))
output = net(x)
print(output.detach().numpy())
# [[ 0.9995001   0.9980063  -0.998006   -0.99977785]
#  [-0.9995007  -0.9980057   0.998006    0.99977785]]

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

net = nn.BatchNorm1d(num_features=4, affine=False, momentum=0.9)
net.set_train()
x = Tensor(np.array([[0.7, 0.5, 0.5, 0.6], [0.5, 0.4, 0.6, 0.9]]).astype(np.float32))
output = net(x)
print(output.asnumpy())
# [[ 0.9995001  0.9980063 -0.998006  -0.9997778]
#  [-0.9995007 -0.9980057  0.998006   0.9997778]]