Image recognition experiment using ResNet18 residual network model of CIFAR10 data set - accuracy of 90% (detailed notes attached)
Auther:Yuandong Li Date: 2020/11/17 Welcome to my github: Li-Y-D The source code of this experiment and the code file in Jupyter Notebook format: Image-classification-CIFAR10-ResNet18
I Test requirements:
Use Jup ...

Posted by cretam on Sat, 07 May 2022 04:50:48 +0300

Cast type
Force tensor to this data type tf. Cast (tensor name, dtype = data type)
Calculate the maximum and minimum values of elements in the tensor dimension
tf. reduce_ Max (tensor name) tf. reduce_ Min (tensor name)
import tensorflow as tf
x1 = tf.constant([1, 2, 3], dtype=tf.float64)
print(x1)
x2 = tf.cast(x1, tf.int32)
print(x2)
pri ...

Posted by PHPycho on Fri, 06 May 2022 13:41:13 +0300

Anomaly detection is to find data points that deviate from the specification. In other words, these points do not conform to the expected pattern. Outliers and exceptions are terms used to describe abnormal data. Anomaly detection is important in all areas because it provides valuable and actionable insights. For example, abnormalities in MRI s ...

Posted by mattsoftnet on Fri, 06 May 2022 13:12:08 +0300

k-nearest neighbors (k-NN) is a basic classification and regression method. Input: the feature vector of the instance, corresponding to the points in the feature space; Output: The class of the instance. When classifying, the new instance is predicted by majority voting according to the class of its k nearest neighbors of the training instance. ...

Posted by kkessler on Thu, 05 May 2022 17:31:35 +0300

ARIMA model
Time series model ARIMA
Application process of ARIMA model
The stationarity is identified according to the scatter diagram, autocorrelation function and partial autocorrelation function diagram of time series.
The non-stationary time series data are smoothed. Until the processed autocorrelation function and partial autocorrel ...

Posted by flunn on Thu, 05 May 2022 02:36:54 +0300

Classical network ResNet
1 Brief description
Networks such as GoogleNet and VGG have demonstrated that deeper networks can abstract more expressive features and thus achieve stronger classification capabilities. In a deep network, with the increase of the network depth, the resolution of the feature map output by each layer is mainly reduced ...

Posted by RDx321 on Wed, 04 May 2022 17:58:02 +0300

NumPy supports a large number of dimensional array and matrix operations. It is a Python library for array operations.
This article is included in Pre machine learning series.
1, Python Basics
Let's first consolidate the basics of Python. Python has six standard data types: Number, String, List, Tuple, Set, and Dictionary. Of which: Immutabl ...

Posted by lanbor on Tue, 03 May 2022 23:33:06 +0300

More code:
Gitee homepage: https://gitee.com/GZHzzz
Blog homepage:
CSDN: https://blog.csdn.net/gzhzzaa
0 is written in front
This article does not involve the depth of each algorithm principle level, the purpose is to help understand these model fusion methods from a macro perspective
1 Voting
Starting from the simplest Voting, this ...

Supervised learning
Supervised Learning Algorithms
Naive Bayes Classifier
Naive Bayes classifiers learn parameters by looking at each feature individually and collect simple class statistics from each feature. Three Naive Bayes classifiers are implemented in scikit-learn: GaussianNB, BernoulliNB, and MultinomialNB. GaussianNB can be applied ...

Posted by atrum on Sun, 01 May 2022 21:50:33 +0300

catalogue
π₯ Personal profile π About the author: β οΈheart_6662, still studying (volume), welcome to exchange and correct~ π π Personal homepage heart blogπ₯ π§ If there are mistakes in the knowledge points of the article, please correct the message π! Learn and make progress with you π£ Series column: Machine Learning π π¬ Maxim: the ...