Cat vs Dog Classifier accuracy vs MAC evaluation

Inspiration

Evaluating tradeoff of accuracy and MAC

What it does

Classify cats vs dogs with varying accuracy and MAC

How we built it

We used tensorflow to create convolutional neural networks

Challenges we ran into

When uploading the data the type was incompatible on several occasions

Accomplishments that we're proud of

We managed to create, train, and test many models in a short span of time

What we learned

For simpler problems simpler models generally have a better accuracy and cost-effectiveness

What's next for Cat vs Dog Classifier accuracy vs MAC evaluation

We will collect more data and design more models before training them on more epoches to determine a better relationship between model size and accuracy and MAC.

Built With

• keras
• python
• tensorflow