235235b2d9
modeldata.h: convert constants to uppercase ( #28769 )
...
old-commit-hash: 32c5e6aafb702a5a17ca7b43c9062ce9e4462d34
2023-07-01 08:26:21 +01:00
d663b5843e
Moonrise Model ( #28761 )
...
* New model: 889463fc-5e5d-497d-9111-c8567a13cabf
* Updated model replay ref
old-commit-hash: 531c13f2acd8d15914aba34a40b356dcb7f02ced
2023-06-30 18:52:20 -07:00
6e547a2748
Modeld: send confidence class ( #28625 )
...
* 0.7
* magic
* faster magic
* more simple
* up
* empty
* more mid bits
* naive
* flatten
* dz
* that can stay
* this is fine
* what the
* what the
* giRevert "what the"
This reverts commit 1619ba68e6098dc581fe9b82e7ecb74562b619cc.
* Revert "what the"
This reverts commit 0037dd368290497a6d0009ca34adb2184b584d2e.
* 1x fine
* that was fine
* combined
* independent cum
* 0 is fine
* use metrics
* up cereal
* process and publish from modeld
* cleanup
* use s.output
* bg
* a greener approach
* dns
* serial
* update ref commit
* rebase
* ref
* cereal master
---------
Co-authored-by: Comma Device <device@comma.ai >
old-commit-hash: ce2dffe56689615597766652576e3711efdb8e61
2023-06-23 16:49:14 -07:00
4ad967f963
Publish navEnabled from modeld ( #28647 )
...
* Publish navEnabled from modeld
* Bump cereal
old-commit-hash: 4c2c73b15282f405900b64b0fb67d461f3058b5c
2023-06-22 19:39:51 -07:00
1fa42d0b97
process_replay: modeld and dmonitoringmodeld support ( #28463 )
...
* vipc support. modeld and dmonitoringmodeld configs
* Update cereal
* Add vision meta
* Use vision meta in process replay
* Exclude modeld and dmonitoringmodeld from test_processes
* Refactor other pieces of code to use vision meta
* remove unnecessary imports
* Add MAX_FRAMES_PER_SEGMENT
* cameraState migration
* Move camera state migration to migration module
* model_replay refactor
* Fix lint issues
* Reduce number of vipc buffers to 2
* Update spinner message
* Update model replay ref
* Support the new log order
* Replace CameraFrameSizes with dict. Add encode_index field
* Migrate camera states based on encode indices
* Refactor process replay
* Refactor model replay
* Remove unnecessary print
* Update model replay ref
* Make camera state migration optional
* Remove unused import
* Add ignore_alive_pubs field
* Add assertion for carParams inside fingerprinting callback
* Remove WideCameraOnly param setup
* Refactor ModeldCameraSyncRcvCallback
* Update model replay ref commit
* Fix camera state migration
* Only migrate camera states when process has vision pubs
* Refactor model replay again
* Fix linter issues
* One more linter fix
* Update model replay ref commit
old-commit-hash: 2c617e0c7a082aeb3217b14e812e5d3c0c26cd4a
2023-06-22 17:36:25 -07:00
31834eac4c
Remove get_model_yuv_transform function ( #28568 )
...
* remove yuv_transform from update_calibration
* Remove get_model_yuv_transform entirely
old-commit-hash: ae5bfcf248e20036998331d5db3cf44c323fe802
2023-06-21 20:02:44 -07:00
77b5e197aa
Enable nav features in modeld ( #28448 )
...
* Enable nav features in modeld
* Enable mapsd/navmodeld
* Updated model_replay_ref_commit and added mapsd/navmodeld to test_onroad
* fixed process name
* always publish from mapsd
old-commit-hash: aadd9ae269e682b6893557a89a02a7ae357206ee
2023-06-16 21:27:35 -07:00
429a638740
New map model: 917a2539-5e7a-4374-878a-9b356f0f1922/500 ( #28579 )
...
old-commit-hash: a9cb25501783bcf2a1e1d7169874481aac897358
2023-06-16 19:31:57 -07:00
990624c07e
Nicolas Cage Model ( #28547 )
...
01697194-d32d-4c3a-a803-d8f61cdf24e9/449 2ff8e6a1-7efd-4984-9f29-974164a3747b/700
old-commit-hash: 4fcd82076aeea11e9636c59ed1d50f740f05c6d1
2023-06-16 13:36:56 -07:00
8aa845a1c8
modeld: use any available stream as main, if there's only one ( #28514 )
...
* Use whatever stream is available as main, if there's only one
* Move logw somewhere else
* Add wideRoadCameraState to ignore_alive if its not available
old-commit-hash: 4eb3d541492f7695227f4d8a83127cbd0d32ff79
2023-06-12 20:13:56 -07:00
eddc84d104
automatically detect available camera streams ( #27640 )
...
* remove WideCameraOnly
* check in set_initial_state
* no block
* remove try block
* apply reviews
old-commit-hash: 4ae0378f639826df5cc1518574842b61b118f371
2023-06-12 13:40:43 -07:00
846cd63f53
thneed: cleanup duplicate GPU config ( #28487 )
...
Co-authored-by: Comma Device <device@comma.ai >
old-commit-hash: b22cadc04d569a6f3593fe32eaec3a3a0e21ef9b
2023-06-11 13:26:41 -07:00
d5564bca27
modeld: adjust CL priority ( #28413 )
...
old-commit-hash: d5101e11ad79af24d77ed3b1b1f8894440cb5233
2023-06-05 17:17:38 -07:00
4de14c1130
hot coffee model ( #28296 )
...
* 1061b1c7-b944-43e3-a940-b56b64d66f54/700
* bump cereal
* bump cereal
* make mypy happy
* write TODO
* read height from written params
* fix certain_if_calib logic and unit tests
* factor moving_avg_with_linear_decay
* remove whitespace
* update model ref commit
* default value for CI
* update process replay ref commit
* update process replay ref commit
* update process replay ref commit
* bump cereal
old-commit-hash: 7925232a349388f3435940c90989f957746d918a
2023-06-02 20:55:13 -07:00
52e1cf2e64
fix input order in onnxmodel ( #28274 )
...
old-commit-hash: d0a8b3780c6ca3db07cbb0a1d644f781efad40f0
2023-05-23 16:11:51 -07:00
22c5053bbc
Nicki Minaj Model ( #28218 )
...
* New model: 2ff7490f-8a2f-4c0d-87a8-b0fa3a4a6a71
* Updated model_replay_ref_commit
old-commit-hash: 328b5d9d47ef24140b316c375665e1cfd00cef31
2023-05-22 15:11:04 -07:00
3c001d5c89
update dm model README ( #28238 )
...
add calib dm input in readme
old-commit-hash: bda0d6ac77b4f1179eea76e8146da6eee5cae983
2023-05-19 15:20:43 -07:00
53b93550c7
update DM model README ( #28211 )
...
* update DM model readme
* rename + permalink + correct types and ranges
old-commit-hash: 2d4558d5cfefe8d5a5080a08ba0ea8bf2869c7e7
2023-05-16 13:40:49 -07:00
fa6e10b739
new model: trained with augmented turn desire pulses ( #28063 )
...
* df733db3-fad2-4485-abe9-59a6a47f2233/449 85f20e13-dd4d-49a8-ba33-98e6afc161d9/700
* update ref commit
old-commit-hash: f80c1087fc022207c252e5b4411fc0f514fb7514
2023-05-01 16:03:16 -07:00
cde221ba7c
new model: trained on new dataset ( #27637 )
...
* df733db3-fad2-4485-abe9-59a6a47f2233/449 946c0f55-247d-4790-a407-c07e4364b340/700
* fix reducel2 df733db3-fad2-4485-abe9-59a6a47f2233/449 946c0f55-247d-4790-a407-c07e4364b340/700
* update ref commit
old-commit-hash: 26541d9e7aa30b1705873e8360b806b52712fde7
2023-03-22 20:19:46 -07:00
0716a1250b
update modeld/models readme ( #27564 )
...
* update readme with new model design
* typo
* space
old-commit-hash: e146bb1a96e98e2dc3d9b777a259044e73a9a633
2023-03-11 16:26:39 -08:00
2fe836f158
tinygrad: bump to 0.5 ( #27505 )
...
* bump tinygrad to 0.5
* update release files
* ref commit + bump tinygrad
* save 220 mW
---------
Co-authored-by: Comma Device <device@comma.ai >
old-commit-hash: 3892c6098085ad05878f78aef0afefac55e38306
2023-03-06 15:50:28 -08:00
0ac73f2a81
MPC path in UI ( #27380 )
...
* 10s lat
* Full length MPC
* redfine N
* Leave controls the same for now
* Updates
* use long plan in lat plan
* interp plan
* simplergit add selfdrive/controls/plannerd.py selfdrive/controls/
* expand to 10s
* revert this
* fix linter
* vizualize
* fix long test
* typo
* cleanup
* compiles
* unused
* unused
* bump cereal
* bump cereal
* use model if no uiplanm
* update replay
* update ref commit
* bump cereal to master
old-commit-hash: eb8bdc0026b49de2fc5107746baeadbd42f58550
2023-02-17 19:58:30 -08:00
542e915982
new model: improved height estimation ( #27234 )
...
* 07a3a2b2-6dbe-43c3-9bb9-a8023932e054/449 c3d7d18a-6207-42e7-84d9-601ecb3c6f0e/700
* 07a3a2b2-6dbe-43c3-9bb9-a8023932e054/449 db92e7f3-3f4b-4f0f-95ff-76cb6ed6894a/700
* update ref commit
old-commit-hash: 1e49c54ffb274a7987626ebfaa8eb3e75ac6fe7c
2023-02-08 22:21:31 -08:00
452031fcc7
new model: fixed weight decay logic ( #27068 )
...
* 07a3a2b2-6dbe-43c3-9bb9-a8023932e054/449 cdfa9e3c-2807-49fc-bdc7-a985f8ff1644/700
* update refs
old-commit-hash: 7316cd03fb71be3e27588cb7a6b9cffafbebe34f
2023-01-26 19:09:12 -08:00
94fc9ef358
tinygrad: update to new version ( #27067 )
...
* tinygrad: bump and retain OPENCL behavior
* add graph.py to release, bump tiny
* update files_common and read from it in scons
* bump with typo fix
* switch tinygrad backend to GPU
* update ref commit
Co-authored-by: Comma Device <device@comma.ai >
old-commit-hash: 64ed44e3b51524ee3412600f647223dc9e7d6f87
2023-01-24 14:06:56 -08:00
b3e47c691b
move all third party stuff into third_party/ ( #26853 )
...
* mv fastcluster
* move msm_kgsl.h
* camerad include
* update path
* mv pyextra
* fix tici build
* add acados_template to release build
Co-authored-by: Comma Device <device@comma.ai >
old-commit-hash: cd8e03d53ed210aec46a2ff728cb4a830314a21a
2022-12-31 21:00:50 -08:00
f315819d47
Navmodel and driving style: update runner ( #26762 )
...
* Navmodel and driving style: update runner
* No driving style yet
* thneedrunner without extra inputs
* nav feature ref
old-commit-hash: 160c9ba1d24c8f5190708dd79bd2682fdadcd736
2022-12-11 15:25:36 -08:00
c2261c5372
navmodeld: only render necessary frames ( #26698 )
...
old-commit-hash: 6e0893299ad435291782e40a92ddeb85b85f4b87
2022-12-05 17:41:32 -08:00
46f70592ae
navmodeld ( #26665 )
...
* Added navmodeld
* New nav model: 7c306685-5476-4bd4-ab65-105b01b6bca8/300, feats only
* little cleanup
* Remove NAV flag
* Moved to_kj_array_ptr to commonmodel.h
* Switch from decimation to last_frame_id check
* add to release files
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com >
old-commit-hash: bb8a38a0508c764c8340e7b16968b06a8367ab7a
2022-12-02 13:14:30 -08:00
30414a7305
Revert "Albert Einstein Model" ( #26576 )
...
Revert "Albert Einstein Model (#26456 )"
This reverts commit 0129c20611bd21fb5b94d19b96d435c7e02041f1.
old-commit-hash: ceb94f1bcd7eae99977e132fd596db353e4e11b4
2022-11-22 11:41:22 -08:00
5bb8ff4a90
Albert Einstein Model ( #26456 )
...
* d0bc247d-9529-4e50-a5dd-95a8a5733874/440 38fb1ce9-18d7-4292-9ffd-678f8483ebf4/700
* update model replay ref commit
old-commit-hash: 34c80a6fbdf8780ad0b75f497c226cf1d9de0ddb
2022-11-18 17:50:24 -08:00
f86b44d516
E2e long model: calibrate model speed to wheel speed ( #26395 )
...
* calibrate!
* Fix test
* Fix proc replay
* check len
* get v_ego from model 8501d20-bb59-4193-aa82-82b2737dedd6/449 609d90f3-65e6-4617-a60c-d6d99eead408/700
* bump cereal
* initialize v_model_error
* typo
* better names
* cleanup
* bump cereal
* update model replay ref commit
* bump to cereal master
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu >
old-commit-hash: f63f0de80a78ade6ad12fe98ea27094035d97457
2022-11-07 17:49:36 -08:00
eafe85c1eb
Model trained with headlight augmentation ( #26284 )
...
* d8501d20-bb59-4193-aa82-82b2737dedd6/449 ddfe2a22-fb0e-4ff0-a97f-0157b95eb44d/700
* update ref
old-commit-hash: c3388d216c33111ae8bd16452016cf8908679c28
2022-10-30 23:55:48 -07:00
4b0d7997ac
Model trained with more long noise ( #26241 )
...
* d8501d20-bb59-4193-aa82-82b2737dedd6/449 d37d320d-7d78-479a-9be2-d58c75284307/700
* Update model ref
old-commit-hash: 2b7290a14261ca0a745f4cd537de7cc9d11ccb12
2022-10-26 00:20:30 -07:00
78f0a175ae
use upstream tinygrad ( #26178 )
...
* use upstream tinygrad
* add networkx to pipfile
* Revert "add networkx to pipfile"
This reverts commit 6cfa164378fa072b325a27040f0388730771437c.
* dont need networkx and update tinygrad
* submodule sync
* add new thneed file
* fix release files
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com >
old-commit-hash: 68e7f42d68232efb89a5dc882fafa71daab72a28
2022-10-21 13:11:50 -07:00
e7d3c730b6
Modeld: Add comment ( #26188 )
...
Rename and add comment
old-commit-hash: 0edbbdeaf9e5c8ad23b73089d2871f88ff29509e
2022-10-21 11:20:52 -07:00
bcb1ba7bfe
Wide transform model ( #26165 )
...
* d8501d20-bb59-4193-aa82-82b2737dedd6/449 f78009d1-2184-4136-9fbc-1c5de55d460d/700
* Change model outs
* Add cereal
* Publish transform
* d8501d20-bb59-4193-aa82-82b2737dedd6/449 f78009d1-2184-4136-9fbc-1c5de55d460d/700
* Bump cereal to master
* Bump cereal to master
* Update model ref
old-commit-hash: d25ab3e3663f1e8a7b08348692d6555fac84e73b
2022-10-21 01:29:58 -07:00
b15ff51d59
Revert "d8501d20-bb59-4193-aa82-82b2737dedd6/449 f78009d1-2184-4136-9fbc-1c5de55d460d/700"
...
This reverts commit 762b554862395cf7d9c7475fae4801a8e0733980.
old-commit-hash: 3a50d5fd852b6d8938fd7974c6966a649cba7ca5
2022-10-21 00:32:34 -07:00
a325c8ca1e
d8501d20-bb59-4193-aa82-82b2737dedd6/449 f78009d1-2184-4136-9fbc-1c5de55d460d/700
...
old-commit-hash: 0ac12b82c770504199f0f9ecad8ab9c6a9b3a470
2022-10-21 00:24:11 -07:00
4323014a2b
desire: give the pulse at t=0 ( #26180 )
...
input desire at t0
old-commit-hash: 6b36f73870bebf467971b5e6020e35ddf1a456c9
2022-10-20 15:13:58 -07:00
426286f24f
DM: add use of e2e preds ( #26078 )
...
* try ml
* de56
* j914ef75a
* jd1124586
* jd1124586
* d112
* oops
* set
* update ref
* use offset
* bump DM power usage
* new ref
old-commit-hash: d522492ba0b80928adc475c1f37b995834c31a90
2022-10-17 19:40:06 -07:00
eec2ca1e8b
CI speedup ( #26096 )
...
* CI speedup
* use the new stuff
* push
* no regressions
* try that
* don't let this slip
* fix modeld tests
* fix linter
* modernize prebuilt
* cleanup
* fix those
* increase a bit
old-commit-hash: 00494a44f4fb8f9e18ce82e22bf40fbe6bc1a805
2022-10-16 15:54:36 -07:00
f428c9de30
Refactor model: no klblock ( #26035 )
...
* ff138dc0-d097-4818-b40e-dba5ba89d5d6/449 13274b7d-b546-4b91-a587-33b4af7dec6a/700
* b1bb39be-c6ce-4744-8e63-92969fda6bfc/449 f3ebfba1-f686-448f-be9b-b4d5010be91c/700
* model ref
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu >
old-commit-hash: b654ebdd25bb3903e94ca5cc6f55d53a256f5c06
2022-10-15 20:04:35 -07:00
523ad86756
faster rocket launcher model ( #26009 )
...
* cache tokens 1456d261-d232-4654-8885-4d9fde883894/440 e63ab895-2222-4abd-a9a5-af86bb70e260/700
* udpate ref commit
* bump tinygrad to master
old-commit-hash: 6c5693e965b9c63f8678f52b9e9b5abe35f23feb
2022-10-07 17:22:42 -07:00
a8ec6f4cfd
Rocket Launcher Model ( #25963 )
...
* 1456d261-d232-4654-8885-4d9fde883894/440 6b7d7cec-ead8-40f3-86cc-86d52c9b03fe/300
* compute only 9 tokens: 1456d261-d232-4654-8885-4d9fde883894/440 6b7d7cec-ead8-40f3-86cc-86d52c9b03fe/300
* tinygrad: cleanup gather
* 1456d261-d232-4654-8885-4d9fde883894/440 6b7d7cec-ead8-40f3-86cc-86d52c9b03fe/700
* empty commit for tests
* bump tinygrad
* dont use tinygrad matmul for now
* bump tinygrad
* 1456d261-d232-4654-8885-4d9fde883894/440 e63ab895-2222-4abd-a9a5-af86bb70e260/700
* float16 1456d261-d232-4654-8885-4d9fde883894/440 e63ab895-2222-4abd-a9a5-af86bb70e260/700
* increase steer rate cost
* Revert "increase steer rate cost"
This reverts commit 74ce9ab9be7ef17ecfec931f96851b12f37f2336.
* fork tinygrad
* empty commit for tests
* basics
* Kinda works
* new lat
* new tuning
* Move LATMPCN so scons compiles
* Update long weights
* Add tinygrad optim
* Update model ref
* update weights
* Update ref
* Try
* Error message for field ignore
* update model regf
* ref commit
* Fix onnx test
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu >
old-commit-hash: cb0b7375b728d1b6e92db68c9ba55f0f54c09a3f
2022-10-05 21:43:38 -07:00
58de00a5db
modeld: removed extra spaces ( #25880 )
...
old-commit-hash: 2f878830c841402cc971b76a3b14e58fc8c69fd9
2022-09-23 10:54:13 -07:00
30326c5a39
Revert "modeld: bug fix in single camera mode of modeld ( #25658 )"
...
This reverts commit 4f058225a71ae8678d890a3183b43475ff26bb60.
old-commit-hash: 48efd8374bf7e484ab0580f344407ab57dcff6c8
2022-09-06 13:00:49 -07:00
fcfa38dc50
modeld: bug fix in single camera mode of modeld ( #25658 )
...
old-commit-hash: 7cdb538043c40f4c30c83863fa52a1fba8c6f621
2022-09-05 17:52:12 -07:00
273fab518b
modeld: delete unused SNPE stuff after move to tinygrad ( #25635 )
...
* delete unused stuff
* remove CL interceptor from thneed since we don't use SNPE anymore
* remove dead files from release
* that's removed
* oops, didn't save
old-commit-hash: 6c39382d71978d20f00286678b2f13e00134bb0a
2022-09-01 18:28:20 -07:00
Dean Lee