I'm looking to create a CNN (probably using ResNet) for automating image rating of videos by processing a predetermined number of frames from the video (60 for example evenly distributed through the video) and those results would feed into the final rating. What would be the best way to setup a network like this? it seems like you would need to run ResNet many times with a chopped off final layer and then somehow feed all of those final layers into a single final dense layer to get the rating. Any advice on how this could be accomplished would be super useful!



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy