YassineYousfi
682857f0cd
MLSIM V3 ( #33745 )
...
* 09366265-2385-4c47-85a9-009aaabc283d/400
* 7a744f78-ac70-4070-b2b2-fd25b736667b/400
* ff6c6166-a9e0-40bc-8867-b0b35bcad8b8/380
* 241215ad-05e1-4153-8fc9-5108c6002123/400
2024-10-09 13:23:52 -07:00
Harald Schäfer
2040f04c45
MLSIM V2 ( #33727 )
...
* bb2f7438-51f1-41ce-b337-238eaf2fd14d/100
* bb2f7438-51f1-41ce-b337-238eaf2fd14d/110
* bb2f7438-51f1-41ce-b337-238eaf2fd14d/330
* c3aa47aa-a00e-4b42-a40b-526039378a3a/400
* bd637aab-4274-41c1-95ac-25fb8bf88547/400
* Update ref
* 5705291a-5f7b-4849-91e8-4b0ea87f44d3/400
* 9f345169-a30d-4fec-bf06-2a457bf0071f/400
* update refs
---------
Co-authored-by: Yassine <yassine.y10@gmail.com >
2024-10-07 09:40:27 -07:00
YassineYousfi
2b486b15c6
MLSIM trained model V1 ( #33698 )
...
* 87c86ea8-9766-43e9-b72f-185496800301/400
* update ref
2024-10-02 14:47:09 -07:00
Harald Schäfer
e442425c9d
MLSIM trained model V0 ( #33676 )
...
* squash f7343ba0-3f7d-4776-9819-2219b8d2d667/270
* fix broken ref
* Model replay ref commit
2024-10-01 02:58:20 -07:00
Harald Schäfer
19bd96004e
Cleanup shift ( #33677 )
...
* Cleanup shift code
* Unsafe buffer copy
* fix bugs
2024-09-29 23:23:16 -07:00
Harald Schäfer
3b08501db3
Game Boy Model V3 ( #33674 )
...
* f4afab38-2ee3-4a71-904a-f2e5d4ec119a/400
* Model replay
* fix onnx cast
* tol
2024-09-29 20:33:35 -07:00
Bruce Wayne
390eee0717
Revert "onnx model needs cast"
...
This reverts commit a2b3b1540d
2024-09-29 20:02:32 -07:00
Bruce Wayne
a2b3b1540d
onnx model needs cast
2024-09-29 19:48:31 -07:00
Harald Schäfer
edf9522bc0
Model and YUV pipeline to uint8 ( #33671 )
...
* Squash
* 78cec5a0-577b-49ac-b443-f7cd327649bd/400
* bump tinygrad
2024-09-28 18:34:31 -07:00
Harald Schäfer
4da090a4e1
Game Boy Model V2 ( #33669 )
...
* 78cec5a0-577b-49ac-b443-f7cd327649bd/400
* ref commit
2024-09-28 15:33:01 -07:00
Harald Schäfer
04a266eaeb
Game Boy Model ( #33661 )
...
* 559069cd-40a6-4456-9052-08659f376ca3/370
* 028fb9bc-b33e-4c26-9cf7-e3c44a85276a/400
* Update ref
* Update tolerance
2024-09-27 22:48:32 -07:00
ZwX1616
876f192112
exec DM model with gpu ( #33609 )
...
* half
old-commit-hash: 9f72eca003d4637ca7fe847ebaf925c694fc2e84
* optimed
old-commit-hash: 6e36e2a12e09275ec21d1590012a92b05ca52ff5
* thneed
old-commit-hash: 419a06c09c0c767d828bcd1e118bc575898c343a
* exec
old-commit-hash: 0059c27ec11b076a37f65d604ed135ea6541b1a6
* runner
old-commit-hash: 34232ada94450ce541eaef546197fa219810a891
* runs but
old-commit-hash: 3db37c00b6a64908293b4de8d8b56e80308cd8f2
* it is 01
old-commit-hash: a160d81eb1a7e77abbef959b44f602610f68f665
* np
old-commit-hash: c1caff6ba648cc2c0094c71b2ea074f01c3c2dc8
* module url
old-commit-hash: 6f4902c4d384263a53e2c1d14d93b5ff864b6a5f
* new
old-commit-hash: 779ae79b1bc3df6374fb6663ac8592e107a6e504
* ds fast
* is this work
* corcention
* real timing
* no reg
* interim gather
* 0e4a9c7b
* fa69be01, and halve
* list
* cleanup
* slighly faster
* setprotlt
* expected
* replay ref
* more powar
* reluctantly
* bump tg
* 8
* less
* less
* bump tg
* better than exp
* closer
* cc
* see diff
* commits
* was right
* to 32 cast
* remove dlc file
* support both
* dspExecutionTime -> gpuExecutionTime
* ignore
* time ref
* ref commit
* last
---------
Co-authored-by: Comma Device <device@comma.ai >
2024-09-26 16:40:44 -07:00
Harald Schäfer
251e2e9400
Clip sigmoid overlfow ( #33635 )
...
* No more C sigmoid
* Clipping
* Need to cast to float
* Update ref
* Clip
* Model refg
2024-09-23 19:06:52 -07:00
Harald Schäfer
e8bea2c78f
Tomb Raider Model ( #33629 )
...
* 69acff08-5383-4103-beea-822f0d228c76/160
* 53f39907-4763-4d19-ba26-e757527c2b61/200
* 21afb89f-1397-4652-b423-abc2da32417a/200
* 21afb89f-1397-4652-b423-abc2da32417a/400
* 53f39907-4763-4d19-ba26-e757527c2b61/400
* 3fb967fd-16a8-4569-ba57-359e54deeab3/395
* Try other policy again
* 3fb967fd-16a8-4569-ba57-359e54deeab3/400
* 0136cabf-539a-4a43-bc7f-06c3654a493c/4400
* 473c0686-1ac9-4c05-9b0b-d1f1afdb6cc3/400
* 83b7993d-51a9-4e3f-904e-3fcd5763c231/400
* 021566c7-cff3-431d-8da2-17a96c888c5f/400
* Fix bugs
* Update longitudinal_planner.py
* Update fill_model_msg.py
* 8be6b59d-4449-42fd-b8e0-93c48387070f/400
* f670a748-3591-4489-a0b3-215118ddad01/400
* 790a2950-c713-4eec-838b-4f55f4fe0ccb/400
* Update model ref
* Plans start at ego
* Update ref
2024-09-23 14:26:28 -07:00
ZwX1616
ffb6e11f96
Revert "exec DM model with gpu" ( #33604 )
...
Revert "exec DM model with gpu (#33397 )"
This reverts commit f79aca8e1e
2024-09-19 20:55:11 -07:00
ZwX1616
f79aca8e1e
exec DM model with gpu ( #33397 )
...
* half
old-commit-hash: 9f72eca003d4637ca7fe847ebaf925c694fc2e84
* optimed
old-commit-hash: 6e36e2a12e09275ec21d1590012a92b05ca52ff5
* thneed
old-commit-hash: 419a06c09c0c767d828bcd1e118bc575898c343a
* exec
old-commit-hash: 0059c27ec11b076a37f65d604ed135ea6541b1a6
* runner
old-commit-hash: 34232ada94450ce541eaef546197fa219810a891
* runs but
old-commit-hash: 3db37c00b6a64908293b4de8d8b56e80308cd8f2
* it is 01
old-commit-hash: a160d81eb1a7e77abbef959b44f602610f68f665
* np
old-commit-hash: c1caff6ba648cc2c0094c71b2ea074f01c3c2dc8
* module url
old-commit-hash: 6f4902c4d384263a53e2c1d14d93b5ff864b6a5f
* new
old-commit-hash: 779ae79b1bc3df6374fb6663ac8592e107a6e504
* ds fast
* is this work
* corcention
* real timing
* no reg
* interim gather
* 0e4a9c7b
* fa69be01, and halve
* list
* cleanup
* slighly faster
* setprotlt
* expected
* replay ref
* more powar
* reluctantly
* bump tg
* 8
* less
* less
* bump tg
* better than exp
* closer
* cc
* see diff
* commits
* was right
* to 32 cast
* remove dlc file
* support both
---------
Co-authored-by: Comma Device <device@comma.ai >
2024-09-19 17:42:44 -07:00
Dean Lee
29dda3b232
Fix FutureWarning "Cython directive 'language_level' not set" ( #33046 )
...
fix FutureWarning
old-commit-hash: fb33366144
2024-07-23 09:27:10 -07:00
Mitchell Goff
e0c89a36da
Notre Dame model ( #32884 )
...
* New model: 6f23a03f-486b-4d3e-a314-19d149644c7c/700
* Bump refs
old-commit-hash: 01c2174d59
2024-07-01 13:59:44 -07:00
Harald Schäfer
f870a968e9
Split cereal into cereal/msgq ( #32631 )
...
* squash
* fix doc
* compile device
* compile device
* Update ref
* add msgq to precommit exclusions
* No service ports
* fix compile
* address comments
* More comments
* Delete logger
* Update opendbc
* Linting
* bump msgq
old-commit-hash: e71ec4e8d7
2024-06-06 14:31:56 -07:00
Dean Lee
6e4c3ddb40
modeld: cleanup commonmodel ( #32618 )
...
cleanup
old-commit-hash: 2482ed085e
2024-06-04 11:20:17 -07:00
Yassine
3ad7205042
Revert "wip /500"
...
This reverts commit 3baaa27c2defbdd4ec29805c2641b9e8a82a35ce.
old-commit-hash: 8bd4540636
2024-05-24 19:45:00 -07:00
Yassine
c40976bb5f
wip /500
...
old-commit-hash: 8183715beb
2024-05-24 19:44:14 -07:00
19igari
5218ec9e60
fix(modeld): Fix for unpredictable behavior in commonmodel_pyx.pyx ( #32482 )
...
Avoid undefined behavior
Co-authored-by: 19igari <koki.igari@turing-motors.com >
old-commit-hash: 25cc8a96ef
2024-05-21 18:41:04 -07:00
ZwX1616
2cb58bbe35
DM: improve e2e predictions ( #32431 )
...
* good but need to freeze quant weights
* pass ref
* pg
* update model reply
old-commit-hash: b8171a1e9c
2024-05-16 13:55:40 -07:00
Harald Schäfer
375978d40b
North Dakota Model ( #32309 )
...
* ND model
* 86d23b15-5c26-464d-9fb5-e857f025462c/700
* Model ref replay commit
* update ref again
old-commit-hash: b9994c7c95
2024-04-29 17:42:49 -07:00
YassineYousfi
9691393bde
WD40 model ( #32141 )
...
* 2eedcd90-b7db-46cb-86be-740f48ded7ab/700
* cleanup some constants
* update model replay ref
old-commit-hash: 6c3a33a6d8
2024-04-09 11:19:43 -07:00
YassineYousfi
75a69e12b3
disable navigate on openpilot ( #32106 )
...
* 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
old-commit-hash: 754dd45ffa
2024-04-09 10:40:38 -07:00
YassineYousfi
5f3960a3a7
duck amigo model ( #31883 )
...
* 026c8008-1728-4549-baf4-ab0436f2927d/700
* update model replay ref
* update again
old-commit-hash: 2aaaa3f167
2024-03-18 16:37:15 -07:00
YassineYousfi
063623602c
Recertified Herbalist Model ( #31616 )
...
* dfa8bce2-a445-45ea-a4b8-e63989b8df08/700
* update model replay ref
old-commit-hash: f1cd16e367
2024-03-01 16:56:33 -08:00
Harald Schäfer
a4d53d378d
Certified Herbalist Model ( #31425 )
...
* ab9921cb-6e0a-4816-bec5-ebb55d37a7f1/700
* 93532291-a562-4ab8-82d2-34d6e9fdcfbb/700
* Update ref
old-commit-hash: 26481d082f
2024-02-19 17:26:10 -08:00
Milan Medić
284450400e
add Cython static analysis ( #31491 )
...
* Adding pre-commit hook for cython static analysis
* Adding changes to cython files to pass static analysis
* Revert "Adding changes to cython files to pass static analysis"
This reverts commit 9a0eb733199abd9eef1eac3d024ef2760348d67c.
* Adding ignore rule for indentation of 4 spaces (E111)
* Fixes for cython-lint static analysis
* Revert "Fixes for cython-lint static analysis"
This reverts commit 972741735b2bdc73460d65a4d7ea167dfc0f4644.
* Adding two new rules into ignore list (2 new lines after difinition of class)
* Adding fixes for cython static analysis
old-commit-hash: 69fb3c2ed5
2024-02-19 12:11:56 -08:00
YassineYousfi
9a6ab74f07
Revert "Certified Herbalist Model" ( #31382 )
...
Revert "Certified Herbalist Model (#31294 )"
This reverts commit 545f5a22dd3fab8aba3299af9560dfe5de409c15.
old-commit-hash: c84e5e2402
2024-02-08 15:31:21 -08:00
Harald Schäfer
ff89f248d0
Certified Herbalist Model ( #31294 )
...
ab9921cb-6e0a-4816-bec5-ebb55d37a7f1/700
old-commit-hash: 06bdc69a02
2024-02-06 08:39:44 +08:00
ZwX1616
8cdd09be5a
DM: Quarter Pounder Deluxe model ( #31170 )
...
* 1
* pg
This reverts commit 71409ec84a3e04e5e7ec960271d4e278a2472462.
* ee new
* 60ab
* update replay
old-commit-hash: ba7f840a06
2024-01-29 16:52:30 -08:00
Harald Schäfer
f9d5fc7dd9
Los Angeles Model 2 ( #31135 )
...
* 7045fb53-6739-4338-8426-20cbd4ad7832/600
* Update constants
* Update parse
* Typos
* Update ref
* 26057144-130f-48e1-8a98-00fae53ae7db/700
* Update ref
old-commit-hash: f55e6a3b81
2024-01-24 15:26:22 -08:00
Harald Schäfer
215b346dc0
Los Angeles Model ( #31037 )
...
* 1c888f5b-c213-4c1c-9eba-c587afd047fc/700
* Move to action
* Updates
* Add steer delay
* Update curvature grep
* clip speed
* No car params for now
* Add delay back
* Update
* fix lint
* fix lint
* update model regf
old-commit-hash: 0067cf3eb1
2024-01-22 00:58:06 -08:00
Mitchell Goff
c24bdc1503
new delhi model ( #30822 )
...
* 027a1efa-10fb-4291-ad58-90cf0ff150b5/700
* debug
* rm for now
* bump refs
* revert that
---------
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com >
old-commit-hash: 7e71fd7bae
2024-01-02 13:27:15 -08:00
YassineYousfi
597529cd6c
blue diamond model 💎 ( #30504 )
...
* c53b1113-ca16-434f-a3e7-457a36ba98cc/700
* 672ee0a5-0466-420d-be18-0610c5d71b6d/700
* update model replay ref commit
old-commit-hash: dd54ec9aa8
2023-12-12 11:24:04 -08:00
Harald Schäfer
b91ecda350
Farmville model ( #30392 )
...
* slightly different
* Revert "slightly different"
This reverts commit 8a470ecab40c295f3b8c777b82cb7a22890d116e.
* d09c9c88-1797-4ed5-ab2d-9dca5b12340b/700
* Update power draw
* Revert "Update power draw"
This reverts commit 1c95b663ec9c507604dd8580ff6386497b5391a8.
* Update ref
old-commit-hash: 9118973ed0
2023-11-07 11:17:37 -08:00
YassineYousfi
91751770a8
(New) Lemon Pie Model 🍋 ( #30209 )
...
* 6f6e3749-1b7c-42e8-a33b-03929b7fc476/700
* oops deleted too much
* 1b4308b7-a659-4ebd-b4c6-c81c1c3890f8/700
* 1be192f3-f407-4217-9757-78b9ad92750a/700
* remove some todos
* more cleanup in lat planner
* vego > min_speed
* regen and update process replay refs
* update model replay ref
* update model replay ref commit again
* Revert "update model replay ref commit again"
This reverts commit 922cb796b8dfe264b0cce7a18206bb898b18bcb3.
* update again
* bump cereal
old-commit-hash: 4c2bd853e4
2023-11-02 14:01:00 -07:00
YassineYousfi
d18f185115
modeld: parsing and publishing in python ( #30273 )
...
* 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 d8807c8348338a1f773a8de00fd796abb8181404.
* confidence: better shape defs
* use ModelConstants class
* fix confidence
* Parser
* slightly more power too
* no inline ifs :(
* confidence: just use if statements
old-commit-hash: cad17b1255
2023-10-19 14:23:51 -07:00
Harald Schäfer
dd8a904c5b
Night Strike Model ( #30148 )
...
* baab2a46-f0c3-46eb-8756-00c55354945b/700
* Update model replay ref
old-commit-hash: 3c0a7d6986
2023-10-03 14:25:30 -07:00
Harald Schäfer
3f1086c410
Optimus Prime Model 🤖 ( #29752 )
...
* b449f295-7e40-4f97-96a6-d858815955e5/700
* make it compile b449f295-7e40-4f97-96a6-d858815955e5/700
* simpler - b449f295-7e40-4f97-96a6-d858815955e5/700
* feature_len changed
* 0a833ab4-9fc7-4e51-a686-9bce3eafcb91/700
* Revert "0a833ab4-9fc7-4e51-a686-9bce3eafcb91/700"
This reverts commit 41708b88447cfcf302b16f21f0caa69450bbd3df.
* 0a833ab4-9fc7-4e51-a686-9bce3eafcb91/700 again
* Update ref
* update ref
---------
Co-authored-by: Yassine <yassine.y10@gmail.com >
old-commit-hash: 3799fe46b3
2023-09-21 13:51:12 -07:00
Mitchell Goff
5732002296
Rewrite dmonitoringmodeld in python ( #29740 )
...
* Added dmonitoringmodeld.py
* Removed dmonitoringmodeld.cc
* Use ModelRunner helpers from runners/__init__.py
* Fixed DriverStateResult field ordering
* Some bug fixes
* Set calib input
* Look ma, no loop!
* Bump dmonitoringmodeld cpu usage in test_onroad
* Fixed memory leak caused by np.ctypes.data_as
* Formatting fixes
* chmod +x
* remove USE_ONNX_MODEL
* Realtime priority 1, formatting fixes
old-commit-hash: 503fa121ee
2023-09-07 19:46:43 -07:00
Mitchell Goff
f9daa1d1cc
Rewrite navmodeld in python ( #29579 )
...
* 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
old-commit-hash: 0c0af682a1
2023-09-07 14:39:37 -07:00
mitchellgoffpc
459e4fdb50
Added cython bindings for commonmodel sigmoid
...
old-commit-hash: 05993f50df
2023-08-31 19:40:53 -07:00
mitchellgoffpc
aca5580900
Move Runtime into runmodel_pyx
...
old-commit-hash: f91e955a86
2023-08-31 13:51:50 -07:00
mitchellgoffpc
e9c82290c0
Remove unnecessary hardware check in modeld
...
old-commit-hash: 857f747467
2023-08-31 13:51:49 -07:00
Mitchell Goff
54988e457f
Move update_calibration to modeld.py ( #29688 )
...
* Move update_calibration to modeld.py
* Updated ref commit
old-commit-hash: 1eb60516cb
2023-08-30 14:12:52 -07:00
Mitchell Goff
c4ae1fae5a
Added USE_THNEED environment variable and removed build flag ( #29645 )
...
old-commit-hash: d998fd88a8
2023-08-29 14:07:57 -07:00
