QA Official

Google Guava Useful Collection Classes 2019-04-07
, Preconditions, precondition judgment No Additional Parameters: No Error Messages in Thrown Exceptions;There is an Object object as an extra parameter: the thrown exception uses Object.toString () as the error message;There is a String Object as an extra parameter, and there is a set of any number of additional Object objects: this variant handles exception messages a bit like printf, but only supports the %s indicator considering GWT compatibility and

MNIST 2019-04-07
MNIST1 import tensorflow as tf import tensorflow.examples.tutorials.mnist.input_data as input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) x = tf.placeholder("float", [None, 784]) W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10])) y = tf.nn.softmax(tf.matmul(x,W) + b) y_ = tf.placeholder("float", [None,10]) cross_entropy = -tf.reduce_sum(y_*tf.log(y)) train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy) init = tf.initialize_all_variables() sess = tf.Session() for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100), feed_dict={x: batch_xs, y_: batch_ys}) # 评估模型 correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1)) accuracy =

MNIST dataset simple version 2019-04-07
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # 载入数据集 mnist = input_data.read_data_sets("MNIST_data", one_hot=True) # 每个批次的大小 batch_size = 100 # 计算一共有多少个批次 n_batch = mnist.train.num_examples // batch_size # 定义两个placeholder x = tf.placeholder(tf.float32, [None, 784]) y = tf.placeholder(tf.float32, [None,

Mnist dataset and code for 2019-04-07
Mnist is an introduction to tensorflow, but many people are stuck on Mnist's data set.Some people cannot find the input_data.pyde code.Therefore, code is provided here for those who cannot find input_data.pyOnly for study.The source code comes from HTTPS://Tensor Flow.Google Flow/+/Master/Tensor Flow/Examples/Tutorials/MN IST/Input _ The following is the code: # Copyright 2015 Google Inc. All Rights Reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); #

Theano(2) RNN training word vector 2019-04-07
1. Brief introduction of the project projectRecurrent Neural Networks with Word EmbeddingsTutorial Address: slot-filling (spoken language understanding) assigns labels to each word in a sentence, which is a classification problem.DatasetThe data set is a small data set of DARPA: ATIS (Airline Travel Information System), expressed by Inside Outside Beginning (IOB)There are 4,978 sentences word 56590 words in the training set of data set.Test set has 893 sentences and word

dropout Principle and Implementation 2019-04-07
Reprinted from: dropout, as a regularization method to prevent CNN from over-fitting, was proposed by Hinton et al. in the 2012 classic paper ImageNet Classification with Deep Convolution.The principle of dropout is very simple: in an iteration of training, the neurons (the total number is n) in each layer are randomly eliminated with probability p, and the data (batchsize samples) in this iteration are trained with the network consisting

java Common Collection Class Summary 2019-04-07
In normal code development, collection classes are often used, such as ArrayList for list cache, Map for mapping, etc Recently, I have focused on the hierarchical inheritance relationship and internal storage structure of the next java collection class, making a summary so that I can turn it over at any time later. java collections, whether List, Set, or Map, are inherited from the collection interface, which mainly defines some public

java Foundation Talk about Collection Classes (Summary and Comparison of Collection Classes) 2019-04-07
Preface: Collection class is a common Base Class Library, and it is a way for java to save objects.It is precisely because they are often used more frequently and speak in a masterful way that it is of great benefit to sum up and summarize them. One. Two Ancestor Interfaces 1)Conllection。A sequence of independent elements, the elements of which are subject to one or more rules, all single-column collection classes implement their interfaces, such as List,Set,Queue.

java's Basic Data Structure 2019-04-07
java Data Structure Introduction Data structure is the way that computers store and organize data.A data structure refers to a collection of data elements that have one or more specific relationships with each other.In general, carefully selected data structures can lead to higher operation or storage efficiency.Data structures are often related to efficient retrieval algorithms and indexing techniques. The data structures commonly used in Java are basically Array array, Collection and Map Collection.

keras installation, win7+ubuntu dual system, gpu,, theano 2019-04-07
originally wanted to use as an introduction.It is said that it was very fast, but after studying for several days, the program could not understand it. So going around made a big circle and finally returned to keras.Learn keras first and then Note here the steps for installing keras (20170625) 1 ubuntu installed Programmers who really enter deep learning should install one.This is not a virtual machine. It