Rene Ranftl

Thanks, works better than I would have expected. With respect to parameters, there really is not much you can play with. The only thing is the resolution at which prediction...

You can only convert to absolute depth if you have additional measurements to resolve the scale and shift ambiguity. See #42 and #4 for similar discussions.

This seems unrelated to MiDaS. I believe you might have naming conflict with some file shadowing the MiDaS namespace. See here: https://stackoverflow.com/questions/59502364/modulenotfounderror-no-module-named-xxx-xxx-is-not-a-package

For 1: The safe way would be to remove the normalization entirely, then perform the process you described. For 2: With MiDaS the only existing solutions is to align scale...

Currently we don't have an analysis along these lines. I'd be interested to see these patterns as it might help us to improve the models. Could you post some example...

We don't have a coral edge tpu at our disposal to try, but after a quick look at the compatibility overview (https://coral.ai/docs/edgetpu/models-intro/#compatibility-overview) it seems that this should be possible in...

Googling suggests that this error is likely due to using a different TensorFlow version than the one that was used to build the model. Our model was tested with 2.3.0...

Thanks for sharing your results. I'm a bit surprised that both CONV_2D and RELU seem to not be mapped to the TPU, as these are certainly supported in principle. Paging...

Thanks for bringing this to our attention. Your are correct. See also #8. Will be fixed in the next revision of the paper.

See here: https://drive.google.com/file/d/1shnlK1E1skzSljvU-PuSbirz8BVLDLqe/view?usp=sharing The images are from the DIW dataset: http://www-personal.umich.edu/~wfchen/depth-in-the-wild/. Please cite/credit this work if you use these images. The IDs after the "_" can be used to identify...