The accuracy calculated from the Keras method evaluation is wrong when using binary_crossentropy when you are using more than 2 labels. You can verify that by recomputing the accuracy yourself. For that, you have to first call the Keras function named "predict" and then calculate the number of correct answers returned by predict. You will get the true accuracy, which is much lower than the Keras "evaluate" one.
For more information regarding the same, do refer to the Machine Learning course.
Certification in Digital Marketing |
Certification in Big Data Analytics |
Certification in Cloud & Devops |
Certification in Full Stack Web Development
Big Data and Data Science Master’s Course |
Data Science Architect Master’s Program |
Cloud and DevOps Architect Master’s Course |
Artificial Intelligence Engineer Master’s Course |
Microsoft Azure Certification Master’s Training
Data Science Course Online |
Big Data Hadoop Certification Training |
Machine Learning Course Online |
Artificial Intelligence Course and Training |
Salesforce Certification Training: Administrator and App Builder |
Tableau Training and Certification Course |
Python Data Science Course & Training |
Ethical Hacking Course |
Business Analyst Course |
Courses in Cyber Security
© COPYRIGHT 2011-2021 INTELLIPAAT.COM. ALL RIGHTS RESERVED.
Download Salary Trends Now !
Learn how professionals like you got up to 100% Salary Hike.