* 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
old-commit-hash: de4031c98e
* 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>
old-commit-hash: 85efde269d
* add sphinx
* switch theme
* Experiment: sphinx docs generation updated (#22708)
* moved build to root gitignore, added .gitkeep
* Improved makefile doc build process
- Removed auto-generated docs from source control
- Moved apidoc.sh into Makefile
- Removed make.bat (can add back if Windows support desired)
- Added sphinx viewcode and markdown extensions
- Added feature to source /docs in build, so any .rst file in /docs will
override the respective file during the build process
- Added feature to copy all markdown/rst files from source into /build/
during build process so they can be easily referenced while writing
docs (see examples in index.md)
- Wrote basic starter index.md file
TODO: Add new dependencies to Pipfile [dev-packages]
* Revert accidental modification to Pipfile
* fix command substitution
* exclude xx
* improve docs
* dont include all docs in release build
* Add dockerfile
* update title
* include normal readme
* build container in CI
* use buildkit
* add login
Co-authored-by: Chad Bailey <chadbailey904@gmail.com>
old-commit-hash: b816b5b644
* c3 is straightforward
* c2 transform
* c3 preview
* alpha model
* Revert "alpha model": wrong quantization data
This reverts commit b50e5739735b30d960aca22bcf3cbe23b0121e13.
* yuv looks good
* a55b
* const int
* block top deadzone
* new box alpha curve
* update k
* fix debug
* rhd use same offset
* box shift for rhd
* 7e3e
* set new thresh
* update ref
* explain
* remove e2e
* same metric thresh
* process isocc
* model
* cancel extra policy
* update numbers
* new model
* update cereal
* up cereal
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 8574e79fec
* 6be443f2-ed70-4580-9c31-61b94d068e24/950
* meta changed too
* new ref
* new ref from CI
* unused
* Revert "new ref from CI"
This reverts commit 28b6bdc81055c39973d0bf9cc964647838b73a73.
* new ref from CI again
old-commit-hash: 72a736f90e
* Revert "New desire model (#21729)"
This reverts commit 709932b3bfb4c3b4f33711b8d07615469e762832.
* Updated process replay ref and reverted release notes
old-commit-hash: 15d6bbb47c
* 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>
old-commit-hash: e83973b9b3
* 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>
old-commit-hash: 4230d5d212
* try this
* use e2e only
* add new outputs
* Revert "use e2e only"
This reverts commit 423dd8e29b88d892074f6f6a0e103681147ff6cc.
* send new
* fix batchnorm
old-commit-hash: 46e3f4528f
* 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
old-commit-hash: 29cc3500a5
* 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>
old-commit-hash: 7ee79c9923
* new model files
* no more rot
* no rot no diag switch
* should be correct and cache aware
* 405d7aeb
* parse new outputs
* change uncertain policy accordingly
* 1bdbd9ed
* adjust
* 0.5 is fine
* 3d4f9cab
* no face prob no loss
* clean up
* clean up test
* update refs
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
old-commit-hash: 8605ba8ab9
* 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>
old-commit-hash: 08846b5c0e
- better polyfitting
- no mpc cost change during lane change
- model trained with better ll gt, sim noise and guaranteed memories
old-commit-hash: 65fcc7c45f
* add traffic convention
* hope this work
* no comment
* latest and gratest
* big gru model
* 1af55c7d-ee15-414a-9e98-a0cb08c3441f/75
* much later in training
* wrong temporal size
* converged
* fix lane changes
old-commit-hash: d3edc594ce
