Davis E. King

Right, I know. I'm just thinking about the sorts of questions I'm likely to get. I've become kind of crotchety as a result of so many ignorant questions :( Anyway,...

You don't need a class. You could just make a global function that returns a bool like, `bool use_cuda()` and put it in the dlib::tt namespace. Then make all the...

Thanks, glad you like dlib :) I'm not sure, I think @OranjeeGeneral was maybe adding one? It's definitely something that would be nice to have.

Right, don't submit that in a PR. If there really is no way to upgrade the con layer without breaking existing stuff then the right thing to do is to...

That's fine. People can get a runtime error if they pass a dilation value other than 1 and are using an old version of cuDNN.

You could use a final layer that resizes the output tensor to whatever size you wanted. So for instance, you could trivially make a layer like the upsample layer that...

I also generally prefer pull requests that address one issue at a time rather than huge pull requests that do a bunch of things at once. The smaller ones are...

Aren't you training with mini-batches where the images are all the same size? You should know the size during training, making setting the output size easy since you know it....

Yes, the cuda side is easy. But a complete PR needs to include a CPU implementation.

Don't do that. Speed isn't a huge deal, but let's not be crazy :)