Martin Bucella

According to the [Conv3D](https://keras.io/layers/convolutional/#conv3d) documentation, Keras supports dilated convolution directly in the `Conv3D` layer if you use the `dilation_rate` parameter.

I've also tried to make `LinearScheduler` work in JIT (see https://gist.github.com/mdraw/f5d9b24d8c43731756be9245ac4eeffb), but I'm not sure how the error in line 28 can be fixed.

It looks like buffer mutation is not yet supported at all in `ScriptModules`, unfortunately: https://github.com/pytorch/pytorch/blob/1409a2afc8d81d911dbcfc2d0b210cf62658237b/test/test_jit.py#L5434.

Since I am also working on grayscale radiology data and needed support for that immediately, I've implemented this in #14. @Pascal900, maybe you can try my branch if this use...

While this is not in the original scope of the project, contributions for license plate detection (or in general other object classes) are welcome as long as the code stays...

This definitely sounds good :) I had actually planned including such a smoothing feature (2.a) from the start but dropped it because I couldn't get it to work properly and...

To save the resulting image it has to be completely re-encoded, so both size changes and a slight drop in image quality can be expected. The relevant code line for...

Thanks for your work @ManuelPalermo, that sounds like a great feature! I'm not sure if everything works as it should with the given default configuration though. I've tested your implementation...

Good idea :+1: A maximum setting would be easy to implement, something like: - `--max-faces=k`: Face detection candidates are sorted by their scores and only the top k candidates are...

Thanks for the report. Did you verify that it worked after removing the alpha channel? To my eyes the error message implies that you have fed in a single-channel grayscale...