James Adams

> Furthermore, do we want to have a similar ability to carry forward other encoding information like compression and such? So we could have a `--preserve-encoding` flag which would trigger...

Other than two test cases that are now somehow off I can approve this. The differences are small/minor from what I can see so far, probably if we compare the...

I've tried to work around this by modifying the model creation section of the `train.py` script ([here](https://github.com/experiencor/keras-yolo3/blob/master/train.py#L117)) from this ```python if multi_gpu > 1: with tf.device('/cpu:0'): ``` to this ```python...

This will be resolved by an upcoming PR for #470

Thanks for this explanation @levisocool The issue is that we re-orient the data within our processing script using NCO. This usually works well on Linux/OSX but usually croaks on Windows....

I am also interested to see if there is an example on how to do this. I have a segmentation dataset with masks for a single class that I'd like...

I'm unfamiliar with a script named `process_grid.py` -- where is that code? Please follow up with the stack trace, as helpful error messages will be contained therein, leading to the...

The NASA video and tutorial use ancient versions of this code. Please re-install from the master branch -- I think you'll get much better results, though there may also be...

Please install from the master branch of this repository. 1. Clone the repository 2. Change into the top-level directory 3. python -m pip install .

@Zeitsperre Yes, Trevor, I'm happy to work this out over one or more video conference calls. Both Teams and Zoom are fine for me. @huard I think option 1 is...