blue‘s blog

sigmoid函数:f(x)=11+e−xf(x)=\frac{1}{1+e^{-x}}f(x)=1+e−x1​import numpy as npdef sigmoid(x): """ x=np.array([]) """ return 1/(1+np.exp(-x))sigmoid梯度:f′(x)=f(x)(1−f(x))f^{'}...

→ 数据的维数→reshape数据维数→ 标准化数据（z-score standardization）；标准化图像只需/255注1.from lr_utils import load_dataset注2. np.reshape()x=np.arange(8)x.reshape(2,4) #reshape成2行4列x.reshape(4,-1) # reshape成4行...

注：用简单得逻辑回归作对比

注：x=np.array([0,0,1,1,1,0,2,2,2])y=np.array([2,2,2,2,1,1,1,1,1])x[y>1]

常用的激活函数有：sigmoid(x)=11+e−xsigmoid(x)=\frac{1}{1+e^{-x}}sigmoid(x)=1+e−x1​- 导数：s′=s(1−s)s^{'}=s(1-s)s′=s(1−s)tanh(x)=ex−e−xex+e−xtanh(x)=\frac{e^{x}-e^{-x}}{e^{x}+e^{-x}}tanh(x)=ex+e−x...

现在tensorflow最高只支持到python3.6，看这里。省事起见，直接安装python3.6（例如Miniconda3-4.3.30.2-Windows-x86_64.exe）点这里选择下载安装好了之后，在pycharm里面设置好，打开。直接pip install tensorflow即可。注：修改python的环境变量...

keras

一些参数的意思：Conv2D二维卷积:keras.layers.convolutional.Conv2D(filters, kernel_size, strides=(1, 1), padding='valid', data_format=None, dilation_rate=(1, 1), activation=None, use_bias=True, kernel_in...