Convolutional Neural Network (CNN) that can classify at ~85% the dog breed from any user-supplied image.
The algorithm accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,
- if a dog is detected in the image, return the predicted breed.
- if a human is detected in the image, return the resembling dog breed.
- if neither is detected in the image, provide output that indicates an error.
-
You can download the dog dataset. Unzip the folder and place it in the repo, at location
path/to/dog-project/dogImages. -
You can download the human dataset. Unzip the folder and place it in the repo, at location
path/to/dog-project/lfw. If you are using a Windows machine, you are encouraged to use 7zip to extract the folder. -
You can donwload the VGG-16 bottleneck features for the dog dataset. Place it in the repo, at location
path/to/dog-project/bottleneck_features.