QA Official

Keras Use Traps

https://qaofficial.com/post/2019/04/28/53802-keras-use-traps.html 2019-04-28
https://keras-cn.readthedocs.io/en/latest/for_beginners/trap/ 1 TF Convolution stone and TH Convolution stone Keras provides two sets of back ends, Theano and Tensorflow.If you have built your own network from scratch, you can rest assured.However, if you want to use an existing network or use a network trained with th/tf as another backend application, you should be especially careful when loading. Convolution stone does not match with the backend used and will not report any errors, because their shape is exactly the same, and there is no method to detect such errors.

Multi-Class Classification Tutorial with the Keras Deep Learning Library

https://qaofficial.com/post/2019/04/28/25654-multi-class-classification-tutorial-with-the-keras-deep-learning-library.html 2019-04-28
Keras is a Python library for deep learning that wraps the efficient numerical libraries Theano and TensorFlow. In this post you will discover how you can use Keras to develop and evaluate neural network models for multi-class classification problems. After completing this step-by-step tutorial, you will know: How to load data from CSV and make it available to Keras. How to prepare multi-class classification data for modeling with neural networks.

Tomcat Sets Hot deployment

https://qaofficial.com/post/2019/04/28/68908-tomcat-sets-hot-deployment.html 2019-04-28
context.xml and server.xml under conf file context.xml: <Context reloadable="true"> server.xml: <Host name="localhost" appBase="webapps" unpackWARs="true" autoDeploy="true"> where autoDeploy=”true " is Hot deployment

covariate shift phenomenon and its solution

https://qaofficial.com/post/2019/04/28/25666-covariate-shift-phenomenon-and-its-solution.html 2019-04-28
When rereading Paper's "Batch Normalization" recently, I found that it repeatedly mentioned a concept "Co-Variant Shift" in the article, and batch-Normalization was proposed to solve the Co-Variant Shift phenomenon in neural networks (especially in deeper networks).I am very interested in this concept, so I took the time to look up some of them and summarize what I learned here today. First of all, let me explain what is called the covariate shift phenomenon.

hdu 2063 (bipartite graph)

https://qaofficial.com/post/2019/04/28/69338-hdu-2063-bipartite-graph.html 2019-04-28
roller coaster Time Limit: 1000/1000 MS (Java/Others) Memory Limit: 32768/32768 K (Java/Others) Total Submission(s): 21687 Accepted Submission(s): 9397

java Generates Digital Fingerprints md5 to Base64

https://qaofficial.com/post/2019/04/28/68897-java-generates-digital-fingerprints-md5-to-base64.html 2019-04-28
cut the crap, code: public String generateToken(){ String tokenString = System.currentTimeMillis() + "" + new Random().nextInt(99999); try { MessageDigest mDigest = MessageDigest.getInstance("md5"); byte[] md5 = mDigest.digest(tokenString.getBytes()); BASE64Encoder encoder = new BASE64Encoder(); return encoder.encode(md5); } catch (NoSuchAlgorithmException e) { // TODO Auto-generated catch block e.printStackTrace(); } return ""; }

mnist library

https://qaofficial.com/post/2019/04/28/49634-mnist-library.html 2019-04-28
mnist library is the most commonly used library, but there are several different versions. 1 https://s3.amazonaws.com/img-datasets/mnist.npz If you use example that comes with keras, you will download it from this address.But for some reason, the download could not come down. http://blog.csdn.net/jsliuqun/article/details/64444302's blog also recorded that it could not be downloaded, using other methods. path = get_file(path, origin='https://s3.amazonaws.com/img-datasets/mnist.npz') f = np.load(path) x_train, y_train = f['x_train'], f['y_train'] x_test, y_test = f['x_test'], f['y_test']

numpy Distinguishing Differences (1)-Reshape and resize

https://qaofficial.com/post/2019/04/28/69151-numpy-distinguishing-differences-1-reshape-and-resize.html 2019-04-28
0. Parameters of Reshape reshape parameter strictly speaking, should be a tuple type (tuple of ints), does not seem to be a tuple into (ints). >>> x = np.random.rand(2, 3) >>> x.reshape((3, 2)) # 以tuple of ints array([[ 0.19399632, 0.33569667], [ 0.36343308, 0.7068406 ], [ 0.89809989, 0.7316493 ]]) >>> x.reshape(3, 2) array([[ 0.19399632, 0.33569667], [ 0.36343308, 0.7068406 ], [ 0.89809989, 0.7316493 ]]) 1. .reshape Realize

python Uses pip 18 Version remote download and Installation Package.

https://qaofficial.com/post/2019/04/28/69705-python-uses-pip-18-version-remote-download-and-installation-package..html 2019-04-28
In many situations where the Internet is isolated, python software packages installed offline are required. Generally, it will be downloaded first on computers with Internet and then copied to computers without Internet for installation. Downloads can be directly downloaded from pypi's website.If there are multiple dependencies, it may be more troublesome. Now a relatively simple command line download method is recommended. pip is a python software management tool.How to install pip will not be described here.

sklearn preprocessing

https://qaofficial.com/post/2019/04/28/25656-sklearn-preprocessing.html 2019-04-28
sklearn preprocessing code code comes from sklearn module in inside, Anaconda (installer) software. init.py """ The :mod:`sklearn.preprocessing` module includes scaling, centering, normalization, binarization and imputation methods. """ from .data import Binarizer from .data import KernelCenterer from .data import MinMaxScaler from .data import Normalizer from .data import StandardScaler from .data import add_dummy_feature from .data import binarize from .data import normalize from .data import scale from .data import OneHotEncoder from .