L-layer Neural Network for classifying cat images from non-cat images. Activation functions, forward propagation and back propagation are manually implemented. Relu is used for hidden layers, sigmoid is used for output layer. Cross-Entropy as a Loss Function. The number of layers is a hyperparameter and is specified in the file TrainNN.py . TrainNN.py trains parameters and writes them to a file weights.pkl . Using TryYourImage you can upload an image and find out if there is a cat on it
-
Notifications
You must be signed in to change notification settings - Fork 0
vdovichevnick/NeuralNetwork_from_scratch
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
L-layer neural network for the very important problem of classifying cat images from non-cat images. :)
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published