Built an image classifer that can be used within a web or mobile app to process real-world, user-supplied images. Given an image of a dog, the classifier has to detect that the image corresponds to a dog and predict the dog's breed. If a human image is submitted, the classifier must detect that the image corresponds to a human! In the case of the image corresponds neither to a dog nor a human, the classifier only has to output that no prediction will be made.
I worked on this project as part of Udacity Artifical Intelligence Nano degree program. You can find my solution here.
To clone the original project repository -
git clone https://github.com/udacity/dog-project.git
cd dog-project
-
Download the dog dataset. Unzip the folder and place it in the repo, at location
path/to/dog-project/dogImages. -
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. -
Download the VGG-16 bottleneck features for the dog dataset. Place it in the repo, at location
path/to/dog-project/bottleneck_features.