- I built the Convolutional Neural Network (CNN) for digits recognition trained on MNIST dataset with keras API (Tensorflow backend).
- The project is very helpful to understand how CNN works at different layers.
- The current best score of this network is 0.9788.
-
Notifications
You must be signed in to change notification settings - Fork 0
I built the Convolutional Neural Network (CNN) for digits recognition trained on MNIST dataset with keras API (Tensorflow backend). The project is very helpful to understand how CNN works at different layers. The current best score of this network is 0.9788.
bendinglight/Number-Detection-With-CNN-In-Keras
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
I built the Convolutional Neural Network (CNN) for digits recognition trained on MNIST dataset with keras API (Tensorflow backend). The project is very helpful to understand how CNN works at different layers. The current best score of this network is 0.9788.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published