Inspiration
A topic I was somewhat familiar with that could be applied with the theme of "upside down"
What it does
Classifies images of upside down dogs and cats.
How we built it
We used a convolutional neural network.
Challenges we ran into
Some challenges we ran into were optimizing the functions and finding the right functions to use.
Accomplishments that we're proud of
Our model being able to correctly classify upside down images and a model training accuracy with over 90%.
What we learned
We learned that CNN's don't particularly struggle with upside down images.
What's next for Upside Down Image Recognition
We can add more animals into our model or predict an image with multiple animals in it.
Built With
- jupyter-notebook
- python
Log in or sign up for Devpost to join the conversation.