mirror of
https://jihulab.com/mr-one/openpilot.git
synced 2026-10-27 21:13:42 +08:00
Comma Device
21c4dd2b41
Applied upstream commit 94a32493e (modeld_v2 chestnut support). Skipped CI workflow files (deleted in this fork). Replaced vendored tinygrad_repo with submodule commit 66ee3cfb4. Rebuilt libparams_c.so for new ModelManager/USBGPU params.
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