Week 5: Document Classification

What kind of data did you include in your training dataset and why?

I included pictures of dogs in set 1 and cats in set 2. This way, the system could tell the differences between detecting dogs and cats.

What other kind of data could have been helpful but maybe you couldn’t get in the short-term/for free?

Some data that could have been useful would be different colors, patterns, and sizes that may be specific to only dogs or cats.

Did your model work well for what you wanted? 

Yes. It can tell the general difference between dogs and cats.

In what instances might your model not work very well? 

If a cat looks very similar to a dog, the system might not tell the difference as well.

Link to project

https://teachablemachine.withgoogle.com/models/5NewKj53g/