Challenge: Can you see the dog in this image?

Here’s an interesting challenge. Can you train a CNN where, if you use the CAM heatmap technique from lesson 7, it highlights the dog in the image here?:

I suspect that our dogs v cats model or even basic imagenet model may be successful. I’d be interested if anyone makes it work!

1 Like

BTW it looks like “dalmatian” is an imagenet category, so you should be able to use it in CAM. :slight_smile:

Hi @jeremy ,

I did a prelim. investigation, and it actually doesn’t look so bad. Here’s the heatmap:

But to be honest. I did cheat a bit. I searched for some google images with the keywords ‘Dalmatian’ and ‘Dalmatian Snow’ and added them to the training set (100 images from each search ) :slight_smile: Of course, I visually inspected to ensure this particular image was not in the download list.

I prolly should’ve also tried with the existing cats/dogs image-set, but I didn’t. I also think solving this problem in the scope of the dog-breeding challenge might shed more insight on the model performance.

Link to the associated ipynb file is here: