QA Official

principles of spring and springMVC parent-child containers

https://qaofficial.com/post/2019/04/01/68321-principles-of-spring-and-springmvc-parent-child-containers.html 2019-04-01
To understand the relationship between these three contexts, you need to be familiar with how spring is started in a web container.Spring's startup process is actually the startup process of its IoC container. For web programs, the startup process of IoC container is the process of establishing context. spring startup process: First of all, for a web application, it is deployed in a web container, which provides a global context environment.

pythonsci kit-learn-svm algorithm

https://qaofficial.com/post/2019/04/01/68371-pythonsci-kit-learn-svm-algorithm.html 2019-04-01
Support Vector Machine (SVM) is a set of supervised learning methods for classification, regression and outlier detection. SVMs: LinearSVC, Linear SVR, SVC, Nu-SVC, SVR, Nu-SVR, OneClassSVM Support Vector Machine has the advantages of effectiveness in high dimensional space. It is still valid when the dimension is larger than the number of samples. A subset of training points (called support vectors) is used in the decision function,

05 keras Basic Use

https://qaofficial.com/post/2019/03/31/23946-05-keras-basic-use.html 2019-03-31
Learning Objectives View model types using plot_model use TensorBoard to view model training Learn basic training of sequence model Learn how to read help documents Foundation Required Python Programming Fundamentals TensorFlow Foundation (to help understand, because keras is still based on TensorFlow) keras Deep Learning Foundation, at least some concepts to know, such as gradient descent, regularization, etc., recommend Wu Enda's deep learning video numpy, matplotlib, pandas, etc import module

Keras: Getting Started Recommendation

https://qaofficial.com/post/2019/03/31/23959-keras-getting-started-recommendation.html 2019-03-31
Keras: Python-based Deep Learning Library keras tutorial

NLP sentiment classification for sentiment analysis

https://qaofficial.com/post/2019/03/31/23997-nlp-sentiment-classification-for-sentiment-analysis.html 2019-03-31
sentiment analysis and sentiment classification sentiment analysis (SENTIMENT ANALYSIS) is a hot research topic at home and abroad in recent years. Its task is to help users quickly acquire, sort out and analyze relevant evaluation information, and analyze, process, induce and reason subjective texts with emotional color. sentiment analysis includes many tasks, such as sentiment classification, opinion extraction, opinion question-and-answer and opinion summary, etc.Therefore, it is difficult to simply classify it into a certain field, and it is often classified into different directions from different angles.

PyTorch's multi-class loss function

https://qaofficial.com/post/2019/03/31/23750-pytorch#39s-multi-class-loss-function.html 2019-03-31
http://blog.leanote.com/post/lincent/PyTorch%E9%87%8C%E7%9A%84%E5%A4%9A%E5%88%86%E7%B1%BB%E6%8D%9F%E5%A4%B1%E5%87%BD%E6%95%B0-2 PyTorch, which has recently become a hot topic, is about to release version 1.0. As one of the best frameworks for all kinds of deep learning tasks, PyTorch provides rich loss functions, and nn.CrossEntropyLoss and nn.NLLLoss are the most frequently used multi-classification tasks. It is worth discussing. nn.CrossEntropyLoss CrossEntropy, as its name implies, is cross entropy. The concept comes from Shannon's information theory and is used to measure the difference information between two probability distributions.

U-net Source Code Analysis (Keras Version)

https://qaofficial.com/post/2019/03/31/23810-u-net-source-code-analysis-keras-version.html 2019-03-31
reprint: https://blog.csdn.net/mielizhi0522/article/details/82217677Source code address: https://github.com/zhixuhao/unet

U-net thesis translation

https://qaofficial.com/post/2019/03/31/23850-u-net-thesis-translation.html 2019-03-31
jianyuchen23' s U-net detailed explanation this blog has already explained very well, but some details are different. I wrote this blog to leave some records for my learning process. summary Training DNN requires a lot of data, which is recognized in the industry.This paper proposes a network structure and a training strategy. The training strategy is based on the use of data enhancement methods in order to make full use of the limited labeled samples.

keras Generates Text Using LSTM

https://qaofficial.com/post/2019/03/31/24040-keras-generates-text-using-lstm.html 2019-03-31
This article mainly introduces the implementation of character-level text generation using LSTM. The following is the sample code: # coding: utf-8 # In[1]: # 下载语料库并将其转化为小写 import keras import numpy as np path = keras.utils.get_file( 'nietzsche.txt', origin='https://s3.amazonaws.com/text-datasets/nietzsche.txt') text = open(path).read().lower() print('Corpus length:', len(text)) # In[11]: ''' 接下来,将提取长度为“ma

keras ImageDataGenerator parameter detailed explanation and usage examples

https://qaofficial.com/post/2019/03/31/23705-keras-imagedatagenerator-parameter-detailed-explanation-and-usage-examples.html 2019-03-31
keras picture generator ImageDataGeneratorkeras.preprocessing.image.ImageDataGenerator(featurewise_center=False, samplewise_center=False, featurewise_std_normalization=False, samplewise_std_normalization=False, zca_whitening=False, zca_epsilon=1e-6, rotation_range=0., width_shift_range=0., height_shift_range=0., shear_range=0., zoom_range=0., channel_shift_range=0., fill_mode='nearest', cval=0., horizontal_flip=False, vertical_flip=False, rescale=None, preprocessing_function=None, data_format=K.image_data_format())Used to generate image data of batch, supporting real-time data promotion.During training, the function will generate data indefinitely until the specified epoch number is reached. parametersfeaturewise_center: boolean value, which de-centers the input data set (with an average value of 0) and executes according to feature samplewise_center: Boolean value, making