Cameron Fabbri
Cameron Fabbri
@noahratliff @richardsj FYI I will be working on fixing this later today
These are interesting, thank you for pointing out some issues. I've only seem similar artifacts when evaluating on images that were far different than the training set, but the shark...
@falrom Nice! I'll have to take a look at the checkpoints I have, it's possible I put up the wrong one. Your trained model looks to be what is expected.
That looks like an old architecture I used. Instead, try the following: `col_img = net.architecture(gray_image, train=False)`