* get log
* simplify two nonsense
* not needed
* libyuv is a joke
* clean up
* try small
* fast but not bad
* working
* clean up driverview
* simplified
* thats mirrored
* smol
* tweak
* ref is screen
* w/ ee
* update camera model
* no if TICI
* start
* update pose thresh
* less cpu more dsp
* new libyuv
* new snpe
* add files
* test
* should be fast
* update out len
* trigger test
* use master snpe
* add cereal
* update cereal
* refactor parsing
* missing ;
* get
* wrong type
* test model
* use driver data
* 10829278-72fe-4283-a118-2cef959ce174/1550
* no pf
* adapt driverview
* ;
* rhd learner
* update libyuv buildi x64
* ad4337ea
* remove blink slack
* test
* no
* use toggle
* b16
* fix for nv12
* 5b02cff5 both
* update test
* update cereal
* update cereal
* update cereal
* v2 packets
* revert libyuv
* no /
* update snpemodel
* ;
* memcpy
* fix test
* use toggle in driverview
* update power
* update replay
* Revert "update replay"
This reverts commit 1d0979ca59.
* update model ref
* halve cpu
* fake 8bit onnx runner
* same thresh as report
* cereal master
Co-authored-by: Comma Device <device@comma.ai>
* update cereal
* run but not use
* log distraction type
* regression scaling
* clean up naming
* add calib buf
* add to header
* fake model
* no calib model
* adjust threshs
* 018a305f
* fix bn
* tweak1
* tweak2
* 0ff2/666
* tweak3
* t4
* t5
* fix out of bound
* skip when replaying old segments
* update ref
* fix onnxmodel
* get calib
* update model replay refs
* up ref
* mse err from 0.028070712 -> 5.8073703e-05
* build with weights fixup
* need thneed lib also
* don't break for binaries
* static analysis says i need init
* check the bias
* load_dlc_weights
* nicer scons
* tested scons
* fix static
* pylint issue
* new ref
* a few more asserts
Co-authored-by: Harald Schafer <harald.the.engineer@gmail.com>
* Fix bigmodel on tici: cam intrinsics arent static
* Give TICI route own name for import
* Make function useable in offline test
* typo
* change tici ecam focal to trained focal
* No shadow variable
* Fixed ref
* Force update this time
* Update model replay ref commit
* Added wide cam vipc client and bigmodel transform logic
* Added wide_frame to ModelState, should still work normally
* Refactored image input into addImage method, should still work normally
* Updated thneed/compile.cc
* Bigmodel, untested: 44f83118-b375-4d4c-ae12-2017124f0cf4/200
* Have to initialize extra buffer in SNPEModel
* Default paramater value in the wrong place I think
* Move USE_EXTRA to SConscript
* New model: 6c34d59a-acc3-4877-84bd-904c10745ba6/250
* move use extra check to runtime, not on C2
* this is always true
* more C2 checks
* log if frames are out of sync
* more logging on no frame
* store in pointer
* print sof
* add sync logic
* log based on sof difference as well
* keep both models
* less assumptions
* define above thneed
* typo
* simplify
* no need for second client is main is already wide
* more comments update
* no optional reference
* more logging to debug lags
* add to release files
* both defines
* New model: 6831a77f-2574-4bfb-8077-79b0972a2771/950
* Path offset no longer relevant
* Remove duplicate execute
* Moved bigmodel back to big_supercombo.dlc
* add wide vipc stream
* Tici must be tici
* Needs state too
* add wide cam support to model replay
* handle syncing better
* ugh, c2
* print that
* handle ecam lag
* skip first one
* so close
* update refs
Co-authored-by: mitchellgoffpc <mitchellgoffpc@gmail.com>
Co-authored-by: Harald Schafer <harald.the.engineer@gmail.com>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
Co-authored-by: Comma Device <device@comma.ai>
* add thneed optimizer
* local work group opt
* kernels and final mods
* release files
* build system touchups
* fix kernel path, rand inputs for self test
* broken since extra is gone
* update model replay ref
Co-authored-by: Comma Device <device@comma.ai>
* 6be443f2-ed70-4580-9c31-61b94d068e24/950
* meta changed too
* new ref
* new ref from CI
* unused
* Revert "new ref from CI"
This reverts commit 28b6bdc810.
* new ref from CI again
* New model: b822ee32-917c-4639-99f8-25be3e6aabad/900
* Enable keeps
* use new packet
* Send keep pulses once per second
* Updated model_replay_ref_commit
* New model: 0f160bf9-1bce-43e6-9785-564b2453eeac
* Bump model_replay_ref_commit
* Bump submodules
* New model: fd904bf9-5dd8-4619-8997-c5668400e078/550
* New model: fd904bf9-5dd8-4619-8997-c5668400e078/950
* No keeps
* Bumped model replay ref
Co-authored-by: Harald Schafer <harald.the.engineer@gmail.com>
* New model: b822ee32-917c-4639-99f8-25be3e6aabad/900
* Enable keeps
* use new packet
* Send keep pulses once per second
* Updated model_replay_ref_commit
* New model: 0f160bf9-1bce-43e6-9785-564b2453eeac
* Bump model_replay_ref_commit
Co-authored-by: mitchell <mitchellgoffpc@gmail.com>
* New model: 51a237cd-9c43-4281-9072-802325e6744d/950
* Added new meta outputs and proper interp for plan_t_arr
* Added meta-based trigger for FCW
* No nans in planner, separate alert for model FCW
* Cleaned up plan_t interp logic
* Added empty cameraError alert to fix unit tests
* Use the normal FCW event
* Updated filter logic
* Updated model replay ref
* Moved disengage predictions into their own cereal struct
* Updated model replay ref for new cereal structs
* Apparently this breaks stuff?
* Bumped cereal commit and model replay ref
* no heading cost
* live mpc weight config
* need to add stds
* make work on empty data
* no divide by 0
* update refs
* update model replay
* update proc replat
* new model replay ref
* New model: 0bf38240-6b55-42b0-bcfb-da08ff5cd0b9/650
* laneless baby
* hardcode model difference for now
* kale toggle
* kale emoji
* sensible description
* make clear it is not just for ui
* emojis dont work yet
* 9671a8fe-539f-4a04-a163-54571df21139/650
* new model
* only read param on rising edge of ignition
* update toggle text
* fix that
* update refs
Co-authored-by: mitchell <mitchellgoffpc@gmail.com>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* start again
* need that too
* this actually works
* not needed
* do properly
* still works
* still works
* still good
* all G without ll
* still works
* all still good
* cleanup building
* cleanup sconscript
* new lane planner
* how on earth is this silent too....
* update
* add rotation radius
* update
* pathplanner first pass
* misc fixes
* fix
* need deep_interp
* local again
* fix
* fix test
* very old
* new replay
* interp properly
* correct length
* another horrible silent bug
* like master
* fix that
* do doubles
* different delay compensation
* make robust to empty msg
* make pass with hack for now
* add some extra
* update ref for increased leg
* test cpu usage on this pr
* tiny bit faster
* purge numpy
* update ref
* not needed
* ready for merge
* try again after recompile
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* Added model_replay and fixed some bugs in camera_replay
* Unpack capnp logs on device
* add sync to device
* GPU now also works on PC
* update model ref
* update refs
* dont change this one
* Use pipeline calib instead of rlog calib
* remove that
* update refs
Co-authored-by: Willem Melching <willem.melching@gmail.com>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* correct indexes
* best metrics yet 30231f46-08af-477e-9d30-776593913c24/700
* sometimes x decreases
* update model refs
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* refactor draw model
* rebase master
* correct valid_len
* rename function
* rename variables
* white space
* rebase to master
* e16c13ac-927d-455e-ae0a-81b482a2c787
* start rewriting
* save proress
* compiles!
* oops
* many fixes
* seems to work
* fix desires
* finally cleaned
* wrong std for ll
* dont pulse none
* compiles!
* ready to test
* WIP does not compile
* compiles
* various fixes
* does something!
* full 3d
* not needed
* draw up to 100m
* fix segfault
* wrong sign
* fix flicker
* add road edges
* finish v2 packet
* Added pytorch supercombo
* fix rebase
* no more keras
* Hacky solution to the NCHW/NHWC incompatibility between SNPE and our frame data
* dont break dmonitoringd, final model 229e3ce1-7259-412b-85e6-cc646d70f1d8/430
* fix hack
* Revert "fix hack"
This reverts commit 5550fc01a7881d065a5eddbbb42dac55ef7ec36c.
* Removed axis permutation hack
* Folded padding layers into conv layers
* Removed the last pad layer from the dlc
* Revert "Removed the last pad layer from the dlc"
This reverts commit b85f24b9e1d04abf64e85901a7ff49e00d82020a.
* Revert "Folded padding layers into conv layers"
This reverts commit b8d1773e4e76dea481acebbfad6a6235fbb58463.
* vision model: 5034ac8b-5703-4a49-948b-11c064d10880/780 temporal model: 229e3ce1-7259-412b-85e6-cc646d70f1d8/430 with permute + pool opt
* fix ui drawing with clips
* ./compile_torch.py 5034ac8b-5703-4a49-948b-11c064d10880/780 dfcd2375-81d8-49df-95bf-1d2d6ad86010/450 with variable history length
* std::clamp
* not sure how this compiled before
* 2895ace6-a296-47ac-86e6-17ea800a74e5/550
* db090195-8810-42de-ab38-bb835d775d87/601
* 5m is very little
* onnx runner
* add onnxruntime to pipfile
* run in real time without using the whole CPU
* bump cereal;
* add stds
* set road edge opacity based on stddev
* don't access the model packet in paint
* convert mat.h to a c++ header file (#2499)
* update tests
* safety first
Co-authored-by: deanlee <deanlee3@gmail.com>
Co-authored-by: mitchell <mitchell@comma.ai>
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: George Hotz <george@comma.ai>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* read rhd from param
* don't need that anymore
* fix build
* bump cereal
* read param from camerad too
* add read_db_bool helper
* bump model replay ref commit, IsRHD wasn't set
* kind of works
* move that
* hack to get camerad to reliably terminate
* not sure why SIGTERM wasn't working before
* compare bytes
* clean up some hacks
* gitignore
* fix that
* WIP
* no reboot
* comparison works
* pretty print
* fix build
* run in jenkins
* python path
* space
* raise timeout
* new eon
* skip the copy
* spinner
* spin less
* update model ref commit
* reenable that
* clean up
* fix jenkinsfile
* parallel
* wrap it in a stage
* fix linter
* better progress
* lower timeout
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
HaraldSchafer
ZwX1616
George Hotz
Adeeb Shihadeh
YassineYousfi
Willem Melching
Mitchell Goff