Nice tutorial, thanks. (Step-by-Step Deep Learning Tutorial to Build your own Video Classification Model)
Only problem (imo) is that it could use a warning about memory requirements I have 8Gs of ram, and upgraded my swap to 16Gs, but still it all fills up at around 30% of images loaded when you try to run your code for storing all the frames as numpi array… so not even the actual training.
Am I doing it wrong? I am using perhaps not the perfect hardware for this all: Jetson Xavier NX. But it’s the best I can do right now.
Kind regards. Hope this helps.