Cutting data is a risky habit to build though. You got lucky that your cameras were the problem, but in most cases those extra 24k near dupes still help the model see small changes in lighting, angle, and motion blur. Take them out and your 91 percent might hold on the test set while falling apart on a new camera you have not seen yet. A better move would have been keeping the data and just adding a dedupe step or weighting the samples, since storage is cheap and retraining is not.

Funny how a close call flips the whole view on hassle.

So you traded a possible career story for a bucket of bottle caps and a horse bit. Next time just flip a coin, at least then you can blame the coin.