Tim Meinhardt

I just tested the example on a Linux machine with the same specifications and got a reasonable output. Is the direct result all zeros or only after saving the image?...

@paggers Did you manage to get it running?

@debinz Since I can not reproduce the Linux problems could you please give me some more info regarding your problem? In particular whether the direct result are all zeros or...

The core C implementation of BM3D we are currently using (see [here](https://github.com/gfacciol/bm3d)) always needs a specific standard deviation of the noise. Do you know any C implementation or resource that...

This would indeed be a great addition. Unfortunately the Adaptive Wiener Filter implementation you provided heavily relies on OpenCV which would introduce a huge new dependency. I will think about...

I extended the `README.rst`, setup script and general interface to support OpenMP multithreading. The `num_threads` parameter can be used to specify the number of working threads. Adding support for OSX...

@YanwenZhu Sorry, but I did not reimplement the original experiments. I applied _Learning to learn_ to an unrelated problem.

There is no dedicated validation set. We validate on a cross-validation split on the training sequences. The split is a per -sequence frame split. See for example `mot17_train_cross_val_frame_0_0_to_0_5_coco` in `src/generate_coco_from_mot.py`....

For the ablation experiments, we use do 50-50 frame split on the training sequences. Training on the first 50% of the frames of each training sequences and validating on the...

(1): Computing the focal loss for a single class introduces some noise which we found to be less if we increase the number of classes. The number 20 is a...