* it's something
* backup
* 16:10
* cleanup
* this is fine
* close
* remove some junk
* no heck
* disos
* real 10
* for some reason this is flipped
* 20hz
* no return
* ae
* tear
* need curve laster
* correct real gains
* fix time
* cleanup
* why the scam
* disable for now
* 0.7
* hdr
* that doesnt work
* what
* hugeoof
* clean up
* cleanup
* fix regs
* welp cant
* is this corrent
* it is sq
* remove
* back
* stg10bit
* back2ten
* Revert "remove"
This reverts commit 18712ab7e1.
* 20hz and swb
* correct height
* 10bit
* ui hack for now
* slight
* perfect
* blk64
* ccm
* fix page faults
* template
* set 4x
* is this fine
* try
* this seems to work
* Revert "this seems to work"
This reverts commit d3c9023d3f.
* needs to be static
* close
* 64 is optimal
* 2
* take
* not 1
* offset
* whats going on
* i have no idea
* less resistence
* box defs
* no
* reduce blur artifacts
* simplify
* fix
* fake short is too much for bright
* can be subzero
* should not use lsvc
* no wasted bit
* cont no slow
* no less than 10bit
* it is based
* wrong
* right
* quart
* shift
* raise noise floor
* 4.5/4.7
* same ballpark
* int is fine
* shane owes me m4a4
* Revert "shane owes me m4a4"
This reverts commit b4283fee18.
* back
* Revert "4.5/4.7"
This reverts commit e38f96e90c.
* default
* oof
* clean up
* simpilfy
* from sensorinfo
* no div
* better name
* not the wrong one
* not anymore relevant
* too
* not call it debayer
* cl headers
* arg is 2nd
* gone is is_bggr
* define
* no is hdr
* rgb_tmp
* p1
* clean up
* 4
* cant for
* fix somewhre else
* const
* ap
* rects
* just set staruc
* nnew tmp
* pull it for now
* 12
* common rect
* Revert "not anymore relevant"
This reverts commit 1d574673a1.
* Revert "too"
This reverts commit c2d4dcc52a.
* Revert "Revert "too""
This reverts commit 0abbabe1fd.
* no tol is fine
* rename
* sensor id
* unsgin
* flag
* some linalg
* cast
* should be h ref
* cap
---------
Co-authored-by: Comma Device <device@comma.ai>
* 2eedcd90-b7db-46cb-86be-740f48ded7ab/700
* noop ciao
* here too
* mapsd too
* update translations
* disable mapsd test from test onroad
* disable mapRenderState test from timings
* lint
* fix exp mode toggle panel
* update tr
* french done
* dont build mapd
* only no nav
* just comment
* deprecate nav fields
* rm not comment
* dont deprecate too much
* remove from services
* merge cereal
* card v1
* fix car events
* fix proc replay
* lets keep that the same
* no extra space here
* move can recv timeouts to card
* organize imports
* organize imports
* slightly bump cpu
* not a card!
* mapsd -> cpu
* link directly to mesa
* Fix gitignore
* without launcher script
* dont change that
* dont need that
* add to files_common
* rename to configure cpu rendering
* without a symlink!
* update time refs
* update ref
* update ref
* remove duplicate include
* bump up again
---------
Co-authored-by: Comma Device <device@comma.ai>
* WIP try modeld all in python
* fix plan
* add lane lines stds
* fix lane lines prob
* add lead prob
* add meta
* simplify plan parsing
* add hard brake pred
* add confidence
* fix desire state and desire pred
* check this file for now
* rm prints
* rm debug
* add todos
* add plan_t_idxs
* same as cpp
* removed cython
* add wfd width - rm cpp code
* add new files rm old files
* get metadata at compile time
* forgot this file
* now uses more CPU
* not used
* update readme
* lint
* copy this too
* simplify disengage probs
* update model replay ref commit
* update again
* confidence: remove if statemens
* use publish_state.enqueue
* Revert "use publish_state.enqueue"
This reverts commit d8807c8348.
* confidence: better shape defs
* use ModelConstants class
* fix confidence
* Parser
* slightly more power too
* no inline ifs :(
* confidence: just use if statements
* Added navmodeld.py
* Deleted navmodeld.cc
* Write SConscript config flags to config.py
* Remove deleted files from release/files_common
* Some more bug fixes
* Added config.py to gitignore
* Get rid of config.py
* Use set_realtime_priority
* A tiny bit more cleanup
* set realtime priority 1
* Use ModelRunner helper class from runners/__init__.py
* Formatting fixes
* mama mia that's a SPICY memory leak
* use OP prefix for logmessage
* cleanup paths too
* cleanup the paths too
* add hw.py to release
* fix those issues
* fix unittests
* fix unittests
* fix unittests
* do swaglog_ipc properly across all the files
* fix that
* fix swaglog in c++
* review suggestions
* Added modeld.py (WIP)
* No more VisionIpcBufExtra
* Started work on cython bindings for runmodel
* Got ONNXModel cython bindings mostly working, added ModelFrame bindings
* Got modeld main loop running without model eval
* Move everything into ModelState
* Doesn't crash!
* Moved ModelState into modeld.py
* Added driving_pyx
* Added cython bindings for message generation
* Moved CLContext definition to visionipc.pxd
* *facepalm*
* Move cl_pyx into commonmodel_pyx
* Split out ONNXModel into a subclass of RunModel
* Added snpemodel/thneedmodel bindings
* Removed modeld.cc
* Fixed scons for macOS
* Fixed sconscript
* Added flag for thneedmodel
* paths are now relative to openpilot root dir
* Set cl kernel paths in SConscript
* Set LD_PRELOAD=libthneed.so to fix ioctl interception
* Run from root dir
* A few more fixes
* A few more minor fixes
* Use C update_calibration for now to exactly match refs
* Add nav_instructions input
* Link driving_pyx.pyx with transformations
* Checked python FirstOrderFilter against C++ FirstOrderFilter
* Set process name to fix test_onroad
* Revert changes to onnxmodel.cc
* Fixed bad onnx_runner.py path in onnxmodel.cc
* Import all constants from driving.h
* logging -> cloudlog
* pylint import-error suppressions no longer needed?
* Loop in SConscript
* Added parens
* Bump modeld cpu usage in test_onroad
* Get rid of use_nav
* use config_realtime_process
* error message from ioctl sniffer was messing up pyenv
* cast distance_idx to int
* Removed cloudlog.infos in model.run
* Fixed rebase conflicts
* Clean up driving.pxd/pyx
* Fixed linter error
Adeeb Shihadeh
cl0cks4fe
ZwX1616
YassineYousfi
Justin Newberry
Harald Schäfer
Shane Smiskol
Mitchell Goff