Too Long; Didn't Read
Classifying video presents unique challenges for machine learning models. As I’ve covered in my <a href="https://medium.com/@harvitronix/continuous-online-video-classification-with-tensorflow-inception-and-a-raspberry-pi-785c8b1e13e1">previous</a> <a href="https://medium.com/@harvitronix/continuous-video-classification-with-tensorflow-inception-and-recurrent-nets-250ba9ff6b85">posts</a>, video has the added (and interesting) property of temporal features in addition to the spatial features present in 2D images. While this additional information provides us more to work with, it also requires different network architectures and, often, adds larger memory and computational demands.