TMC Member jimmy_d, who describes himself as a “deep learning dork,” has dropped some interesting details on the capability of Autopilot with Tesla’s new software version 9.
Jimmy_d’s sleuthing suggests that Tesla has made significant improvements to its neural net that allows the system to better leverage all 8 cameras around the car.
“Like V8 the V9 NN (neural net) system seems to consist of a set of what I call ‘camera networks’ which process camera output directly and a separate set of what I call ‘post processing’ networks that take output from the camera networks and turn it into higher level actionable abstractions,” he wrote. “So far I’ve only looked at the camera networks for V9 but it’s already apparent that V9 is a pretty big change from V8.”
Jimmy_d says the V9 network takes 1280×960 images with 3 color channels and 2 frames per camera, which amounts to 13-times more data than V8.
“This V9 network is a monster, and that’s not the half of it,” he wrote. “When you increase the number of parameters (weights) in an NN by a factor of 5 you don’t just get 5 times the capacity and need 5 times as much training data. In terms of expressive capacity increase it’s more akin to a number with 5 times as many digits. So if V8’s expressive capacity was 10, V9’s capacity is more like 100,000. It’s a mind boggling expansion of raw capacity.”
“As a neural network dork I couldn’t be more pleased,” he wrote.
Check out the full post and comments here.