mxnet基础到提高(53)-批量标准化（2）

moving_mean = moving_mean * momentum + data_mean * (1 - momentum)
moving_var = moving_var * momentum + data_var * (1 - momentum)

如果use_global_stats设置为true，则使用moving_mean和moving_var代替data_mean和data_var来计算输出。在推理过程中经常使用。

参数axis指定输入形状的哪个轴表示“通道”（单独的标准化组）。默认值为1。指定-1将通道轴设置为输入形状中的最后一项。

当fix_gamma设置为True时，不提供稀疏支持。如果fix_gamma设置为False，稀疏张量将回退。

gamma和beta都是可学习的参数。但如果fix_gamma为真，则将gamma设置为1，并将其渐变设置为0。

Parameters
data (NDArray) – Input data to batch normalizationgamma (NDArray) – gamma arraybeta (NDArray) – beta arraymoving_mean (NDArray) – running mean of inputmoving_var (NDArray) – running variance of inputeps (double, optional, default=0.0010000000474974513) – Epsilon to prevent div 0. Must be no less than CUDNN_BN_MIN_EPSILON defined in cudnn.h when using cudnn (usually 1e-5)momentum (float, optional, default=0.899999976) – Momentum for moving averagefix_gamma (boolean, optional, default=1) – Fix gamma while traininguse_global_stats (boolean, optional, default=0) – Whether use global moving statistics instead of local batch-norm. This will force change batch-norm into a scale shift operator.output_mean_var (boolean, optional, default=0) – Output the mean and inverse stdaxis (int, optional, default='1') – Specify which shape axis the channel is specifiedcudnn_off (boolean, optional, default=0) – Do not select CUDNN operator, if availablemin_calib_range (float or None, optional, default=None) – The minimum scalar value in the form of float32 obtained through calibration. If present, it will be used to by quantized batch norm op to calculate primitive scale.Note: this calib_range is to calib bn output.max_calib_range (float or None, optional, default=None) – The maximum scalar value in the form of float32 obtained through calibration. If present, it will be used to by quantized batch norm op to calculate primitive scale.Note: this calib_range is to calib bn output.out (NDArray, optional) – The output NDArray to hold the result.Returns
out – The output of this function.Return type
NDArray or list of NDArrays

mxnet基础到提高(53)-批量标准化（2）相关推荐

mxnet基础到提高(53)-ndarray与numpy之间转换
from mxnet import nd import numpy as np x = nd.array(((1,2,3),(5,6,7))) y1=x.asnumpy() y2=nd.array(y ...
mxnet基础到提高(6)--梯度,反馈与标准化（归一化）
1.attach_grad(grad_req='write', stype=None) 附加一个梯度缓存在NDArray上,这样,回退(反馈)能计算相应的梯度参数: grad_req ({'writ ...
mxnet基础到提高(51)-Activation激活函数
mxnet.ndarray.Activation(data=None, act_type=_Null, out=None, name=None, **kwargs) Applies an activa ...
mxnet基础到提高(49)-使用免费的云jupyter
强大而免费的GOOGLE 云jupyter notebook https://colab.research.google.com/notebooks/intro.ipynb#recent=true 什 ...
mxnet基础到提高(48)-ones和ones_like
返回全1元素矩阵 mxnet.ndarray.ones(shape, ctx=None, dtype=None, **kwargs)[source] Returns a new array fille ...
mxnet基础到提高(46)-ndarray.zeros,CSRNDArray稀疏矩阵
mxnet.ndarray.zeros(shape, ctx=None, dtype=None, stype=None, **kwargs)[source] 返回一个新的array数组,指定shape ...
mxnet基础到提高(44)-ndarray.arange创建行向量
mxnet.ndarray.arange(start, stop=None, step=1.0, repeat=1, infer_range=None, ctx=None, dtype=<cla ...
mxnet基础到提高(43)-编译安装
因为pip方式安装,不能安装c++接口,此外,此方式安装的包,是使用默认参数编译的,很多运行环境要求使用指定参数编译,比如,不支持GPU,不支持SSE,还有嵌入式环境或上网本等低档设备以及端设备运行. ...
mxnet基础到提高(40)-ndarray之运算(1)
# -*- coding: utf-8 -*- """ Spyder EditorThis is a temporary script file. "" ...

mxnet基础到提高(53)-批量标准化（2）

mxnet基础到提高(53)-批量标准化（2）相关推荐

最新文章

热门文章