Skip to content

tazriahelal/Different-Custom-CNN-Image-Classificataion-Cifer10

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Hi, I'm Tazria! 👋

Different-Custom-CNN-Image-Classificataion-Cifer10

Neural Network practice sheet

🚀 About Me

I'm a backend developer & Data Science enthusiast.

🛠 Skills

Java-Spring Boot Python3-Flask, SciPy, TensorFlow, Keras

🚀 Topic-

Basic concept for a neural netwrok like- strides, filters, convplution and fully connected neural network. Also end to end basic code understanding.

The CIFAR-10 dataset includes 60,000 color images with a resolution of 32 by 32 pixels, organized into 10 categories with 6,000 pictures in each category. There are 50,000 photos used for training and 10,000 images used for testing.

The dataset is separated into six batches: five for training and one for testing, with each batch containing 10,000 photos. The sample set includes precisely 1000 photos taken at random from each category. The remaining photos are placed in a random sequence inside the training batches. Nevertheless, some training batches may have a greater number of examples from one category than from another. The training batches have precisely 5000 examples from each category. Together, they make up the training set.

🔗 Links

linkedin