mxnet基础到提高(27)-Dense

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Fri Aug 10 16:13:29 2018@author: myhaspl
"""
from mxnet import nd
from mxnet.gluon import nn
layer = nn.Dense(2)#输出
layer.initialize()
x = nd.random.uniform(-1,1,(3,4))#输入3组数据
layer(x)
w=layer.weight.data()#权值，数据为4个元素，因此权值也是4个元素
print w
print w.shape
print x

[[-0.00873779 -0.02834515 0.05484822 -0.06206018]
[ 0.06491279 -0.03182812 -0.01631819 -0.00312688]]
<NDArray 2x4 @cpu(0)>
(2L, 4L)

[[ 0.09762704 0.18568921 0.43037868 0.6885315 ]
[ 0.20552671 0.71589124 0.08976638 0.6945034 ]
[-0.15269041 0.24712741 0.29178822 -0.23123658]]
<NDArray 3x4 @cpu(0)>

mxnet基础到提高(27)-Dense相关推荐

mxnet基础到提高(36)-单层神经网络
构造一个4个输出的单层网络, import mxnet.ndarray as nd from mxnet.gluon import nnlayer1=nn.Dense(4)#权重默认为平均分布的[-0 ...
mxnet基础到提高(4)-－ Dense层基础
from mxnet import nd from mxnet.gluon import nn x = nd.array(((1,2,3),(5,6,7))) #创建神经网络第一层密集层,Dense会 ...
mxnet基础到提高(7)--卷积神经网络基础(2)
构造具有灵活正向函数的网络创建nn.Block一个子类和实现两种方法: from mxnet import nd from mxnet.gluon import nn class MixMLP(nn ...
mxnet基础到提高(5)-－卷积神经网络基础(1)
通过nn.Sequential构造LeNet ,MXNet将自动构造向前函数,按顺序执行添加的LeNet 卷积神经网络是一种特殊的多层神经网络.与几乎所有其他神经网络一样,它们都经过了反向传播算法的训 ...
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(27)-Dense

mxnet基础到提高(27)-Dense相关推荐

最新文章

热门文章