modeld: use correct intrinsics for extra transform when wide camera disabled#38239
modeld: use correct intrinsics for extra transform when wide camera disabled#38239Quantizr wants to merge 1 commit into
Conversation
|
Ran some tests to see how close the model path is to original given the weirdly warped big_img, this change leads to a consistent noticeable improvement. The old version still drives well enough that I've been using it for almost a year as the current models barely look at the big_img (in fact, if you just put a static gray for big_img the model drives alright). On the other hand, only using the wide cam and cropping for the narrow cam with Time-weighted lateral path deviation in meters vs typical two camera setup across 38 segments:
|
Process replay diff reportReplays driving segments through this PR and compares the behavior to master. ✅ 0 changed, 66 passed, 0 errors |
Description
DISABLE_WIDE_ROADflag currently leads to using the ecam intrinsics on the narrow cam for the big_img model input. This PR uses the proper intrinsics if the wide camera is not available.