Good question. Detecting just one class (in this case, cats) will require negative examples. Finding good negatives is somewhat of challenging task because they should be pretty comprehensive, but if you create an…
Oh, if you don't want to get into the nitty gritty of it, you should use Digits (https://github.com/NVIDIA/DIGITS). This is the easiest way to setup a CNN and train it with your sample images (at least compared to…
Good question. Detecting just one class (in this case, cats) will require negative examples. Finding good negatives is somewhat of challenging task because they should be pretty comprehensive, but if you create an…
Oh, if you don't want to get into the nitty gritty of it, you should use Digits (https://github.com/NVIDIA/DIGITS). This is the easiest way to setup a CNN and train it with your sample images (at least compared to…