m0_51328444的博客

1.Sequentialget_last_output=K.function([model.layers[0].input],[model.layers[-1].output])permute_layer_output = get_last_output([x_test1])[0]可以指定是训练还是测试当有Dropout和BN层时不推荐使用该方法2.Modelmiddle = Model(inputs=model.input,outputs=model.get_layer('dense').o

1.pandas无法打开.xlsx文件from openpyxl import Workbook,load_workboodata=pd.read_excel('D:/accidents.xlsx',index_col='DATE',engine='openpyxl')

用tensorflow 保存变量import tensorflow as tfimport numpy as np# save to file#remember to define the same dtype and shape when restoreW=tf.Variable([[1, 2, 3], [4, 5, 6]], dtype=tf.float32, name='Weights') # 最好给个dtypeb=tf.Variable([[1, 2, 3]], dtype=tf.f

import tensorflow as tfimport numpy as npfrom tensorflow.examples.tutorials.mnist import input_data#number 1 to 10 datamnist=input_data.read_data_sets('MNIST_data',one_hot=True)def compute_accuracy(v_xs,v_ys): global prediction #全局变量 y_pre=s

#使用sklearn之前要装scikit-learn这个包from sklearn.datasets import load_digitsfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import LabelBinarizer#load datadigits=log_digits()X=digits.data #加载从0到9的digits datey=digits.target #

添加输入def add_layer(inputs,in_size,out_size,n_layer,activation_function=None): layer_name='layer%s'%n_layer#输出结果为layern_layer,以字符串形式编辑神经层 tf.summary.histogram(layer_name+'weights',Weights)#纵轴是weights,表示的是Weights tf.summary.histogram(layer_name+'.

inputs可视化with tf.name_scope('inputs'): xs=tf.placeholder(tf.float32,[None,1],name='x_input')#None是无论给多少sample都OK ys=tf.placeholder(tf.float32,[None,1],name='y_input')hidden layer可视化def add_layer(inputs,in_size,out_size,activation_function=.

import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plt#添加神经层def add_layer(inputs,in_size,out_size,activation_function=None): Weights=tf.Variable(tf.random_normal([in_size,out_size]))#用random比用0好 biases=tf.Variable(tf.zeros

import tensorflow as tfimport numpy as np#添加神经层def add_layer(inputs,in_size,out_size,activation_function=None): Weights=tf.Variable(tf.random_normal([in_size,out_size]))#用random比用0好 biases=tf.Variable(tf.zeros([1,out_size])+0.1) #biases推荐的值不为

import tensorflow as tf#添加神经层def add_layer(inputs,in_size,out_size,activation_function=none) Weights=tf.Variable(tf.random_normal[in_size,out_size])#用random比用0好 biases=tf.Variable(tf.zeros([1,out_size])+0.1) #biases推荐的值不为0 Wx_plus_b=tf.matm

import tensorflow as tfinput1=tf.placeholder(tf.float32)#一般处理float 32input2=tf.placeholder(tf.float32)output=tf.multiply(input1,input2)with tf.Session() as sess: print(sess.run(output,feed_dict={input1:[7.],input2:[2.]})) #placeholder用于占位，fee

import tensorflow as tfstate=tf.Variable(0,name='counter')#定义变量state,初始值为0，名字是'counter'one=tf.constant(1)new_value=tf.add(state,one)update=tf.assign(state,new_value)#把new_value的值赋给stateinit=tf.initialize_all_variables()#定义变量必备with tf.Session() as se