9c7833faf9
* Vegetarian Filet o Fish model * fix.. atc.. * test cluster_speed_limit * fix.. cluster_speed_limit.. 2 * fix.. clusterspeedlimit3 * cruise speed to roadlimit speed * fix.. * fix.. eng * deltaUp/Down for lanechange * fix.. atc desire... * fix.. * ff * ff * fix.. * fix.. eng * fix engsound * Update desire_helper.py * fix.. connect... * fix curve_min speed * Revert "fix curve_min speed" This reverts commit fcc9c2eb14eb3504abef3e420db93e8882e56f37. * Reapply "fix curve_min speed" This reverts commit 2d2bba476c58a7b4e13bac3c3ad0e4694c95515d. * fix.. auto speed up.. roadlimit * fix.. atc auto lanechange... * Update desire_helper.py * Update cruise.py * debug atc... * fix.. waze alert offset.. * fix.. * test atc.. * fix.. * fix.. atc * atc test.. * fix.. atc * fix.. atc2 * fix.. atc3 * KerryGold Model. latsmooth_sec = 0.0 * lat smooth seconds 0.13 * fix comment * fix.. auto cruise, and speed unit * change lanemode switching. * erase mazda lkas button.
Each model should be a clean single file. They are imported from the top level `models` directory It should be capable of loading weights from the reference imp. We will focus on these 5 models: # Resnet50-v1.5 (classic) -- 8.2 GOPS/input # Retinanet # 3D UNET (upconvs) # RNNT # BERT-large (transformer) They are used in both the training and inference benchmark: https://mlcommons.org/en/training-normal-21/ https://mlcommons.org/en/inference-edge-30/ And we will submit to both. NOTE: we are Edge since we don't have ECC RAM