e4567c3cf8
v2 packets
3 years ago
12d742153c
5b02cff5 both
3 years ago
fbf1d2f581
fix for nv12
3 years ago
472566faac
b16
3 years ago
f49a9c9fd2
less TICI when not needed ( #24698 )
...
* less TICI when not needed
* fix process replay
* move reading voltages into hw abstraction layer
* Update selfdrive/hardware/tici/hardware.h
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* Update selfdrive/hardware/hw.h
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* Update selfdrive/hardware/base.h
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* rename init function
* Update selfdrive/athena/athenad.py
Co-authored-by: Robbe Derks <robbe.derks@gmail.com>
* Update selfdrive/boardd/boardd.cc
* Apply suggestions from code review
* Update selfdrive/thermald/thermald.py
* update ref
* fix alert width if all cameras are bad
* add ecam to test_loggerd
* bump cereal
* bump cereal
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
Co-authored-by: Robbe Derks <robbe.derks@gmail.com>
3 years ago
ea5b8cdfb1
nv12: encoderd avoids a full frame copy ( #24519 )
...
* rgb to nv12
* nv12 works (w memcpy)
* correct now
* no copy
* fix nv12 with fast debayer
* reverts of unused stuff
* ui use nv12
* comment out thumbnails for now
* rebase fix
* dm read nv12
* model read nv12
* fix ffmpeg encoder
* thumbnails from nv12
* replay to nv12
* python framereader support nv12
* remove hardcoded frame/buffer sizes
* fix build
* ffmpeg encoder fix buffers
* small cleanup
* reduce power usage test
* fix cpu usage test
* fix snapshot
* fix loggerd test
* bump cereal
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: Joost Wooning <jwooning@gmail.com>
3 years ago
b5aed2bf67
Simulator: Speed up process by removing second camera ( #24679 )
...
* simulator: support running wide camera only
* proper frame id
* use param name that makes more sense
* do some cleanup
* Update tools/sim/bridge.py
Co-authored-by: Willem Melching <willem.melching@gmail.com>
3 years ago
32a9ccfc37
visionipc python shim ( #24660 )
3 years ago
3a79a729f0
test
3 years ago
7da48ebdba
New model: better laneless ( #24605 )
...
* Fix ping pong
* Fix hugging: e6fd3a62-aa86-46d1-a414-19137ed1babc/800
* Remove lateral toggle
* a6da6265-1952-48dd-986b-2b5996dd2642/950
* Model replay commit
* Revert "Remove lateral toggle"
This reverts commit 69e57eb7e1
3 years ago
1cc652602f
Small fixes for macOS build ( #24620 )
...
* Small fixes for macOS build
* remove gpu_libs
3 years ago
1be244ff4a
ad4337ea
3 years ago
cb8885cffb
Merge common/ and selfdrive/common ( #24556 )
...
* Merge common/ and selfdrive/common
* fix that
* fix version
* fix unit tests
3 years ago
e2e5378dd3
Revert "Joint model ( #24521 )" ( #24581 )
...
This reverts commit 7996fd37ef
3 years ago
0fc4b4df98
thneed: add flag to enable optimizer ( #24568 )
...
* improve the thneed compiler
* only init thneed if we are using the GPU
Co-authored-by: Comma Device <device@comma.ai>
3 years ago
7996fd37ef
Joint model ( #24521 )
...
* update models
* wip lanelines mhp parsing
* typos
* newer models
* 95995a49-db0c-4261-8776-b90780dc2a8c/600
* Use laneful policy to prevent planner aggression
* c8c3ab69-bd2c-4d1c-a7f8-9e8457e4827b/950
* ede8f75a-df3e-41fb-bc56-63e2f33858e5/950
* 7205c5af-7532-4215-ad9b-678789054db7/995
* bfb34fa3-1d72-4987-854f-43d42ee01015/950
* change cost
* 8ae2477a-b452-4601-b04c-d3af66ea5e98/950
* Update heading cost
* 9b991314-94f5-4f0b-872e-58d95266e4d0/333
* 9b991314-94f5-4f0b-872e-58d95266e4d0/950
* ede8f75a-df3e-41fb-bc56-63e2f33858e5/950
* undo lateral planner changes
* rm whitespace
* update ref
* c0acc19d-f2f1-47ae-8838-5382c6c6c7f5/950
* c0acc19d-f2f1-47ae-8838-5382c6c6c7f5/950
* update model refg
* Update model ref
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu>
3 years ago
319f3d1475
move models to selfdrive/modeld/ ( #24539 )
...
* move models to selfdrive/modeld/
* two more refs
3 years ago
ef81afc354
Revert "Joint Model ( #24213 )"
...
This reverts commit eff08cb17f
3 years ago
eff08cb17f
Joint Model ( #24213 )
...
* update models
* wip lanelines mhp parsing
* typos
* newer models
* 95995a49-db0c-4261-8776-b90780dc2a8c/600
* Use laneful policy to prevent planner aggression
* c8c3ab69-bd2c-4d1c-a7f8-9e8457e4827b/950
* ede8f75a-df3e-41fb-bc56-63e2f33858e5/950
* 7205c5af-7532-4215-ad9b-678789054db7/995
* bfb34fa3-1d72-4987-854f-43d42ee01015/950
* change cost
* 8ae2477a-b452-4601-b04c-d3af66ea5e98/950
* Update heading cost
* 9b991314-94f5-4f0b-872e-58d95266e4d0/333
* 9b991314-94f5-4f0b-872e-58d95266e4d0/950
* ede8f75a-df3e-41fb-bc56-63e2f33858e5/950
* undo lateral planner changes
* rm whitespace
* update ref
Co-authored-by: Harald Schafer <harald.the.engineer@gmail.com>
3 years ago
17e33978cd
Mypy fixes for --check-untyped-defs ( #24372 )
...
more type fixes
3 years ago
d5b244c7b0
missing ;
3 years ago
1af6c77f81
refactor parsing
3 years ago
a57c234696
update out len
3 years ago
60b7114024
onnxruntime: initialize CUDA provider before predictions ( #24330 )
...
* initialize CUDA runtime before predictions
* dmond pauses modeld execution...
* done in other PR
4 years ago
3741908733
Do not run model when skipping frames ( #23949 )
...
* Do not run model when skipping frames
* also prepare wide
* add logging
* remove newline
* small skip test
* more random
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
4 years ago
f4ea7ec053
should be fast
4 years ago
40ca9cb4f4
test
4 years ago
b445e50033
less cpu more dsp
4 years ago
27b067446a
modeld tests ( #24263 )
4 years ago
40cf4a7498
Update SNPE to 1.61.0.3358 ( #24253 )
...
* update snpe to snpe-1.61.0.3358
* fix new snpe build
* fix snpe dir in files_tici
Co-authored-by: Comma Device <device@comma.ai>
4 years ago
5c48e7bc86
remove comma two support ( #24248 )
...
* remove comma two support
* cleanup release files
* little more
* more libs
* no more gralloc
* add snpe back
4 years ago
6dfdb04cb4
Remove visiontest files ( #24219 )
4 years ago
b5c91f851f
fast but not bad
4 years ago
3b2fda2a39
try small
4 years ago
b37de23427
clean up
4 years ago
4775ae1e43
libyuv is a joke
4 years ago
dde1e1927b
not needed
4 years ago
439862c7db
simplify two nonsense
4 years ago
ac6ab2ddc7
get log
4 years ago
65fca83abe
Latency logging 2 ( #24058 )
...
* msg_order and gantt
* frameId in long/lat planner
* track frame id
* controls frame id
* graph tracked events
* graph json
* cloudlog timestamp
* c++ cloudlog
* add frame id
* bug fixes
* bug fixes
* frame id visionicp
* bug fixes and debug level
* timestamp log placement
* print timestamps in table
* translate events
* more logging
* bug fixes
* daemon boardd
* print logs with boardd
* more timestamp logs
* cleanup
* remove publish logs
* bug fix
* timestamp received
* timestamp received
* bug fixes
* use json lib
* ignore driver camera
* prep for new timestamp pipeline
* bug fix
* read new pipeline unfinnished
* read new pipeline
* bug fix
* add frame to controlsstate
* remove controlsstate
* print
* cleanup
* more cleanup + bug fix
* clock build issue
* remove unused imports
* format durations
* increase speed
* pr comments fixes
* conflicts
* set MANAGER_DAEMON for boardd
* clean script code
* bug fix + argparse
* remove rcv time
* bug fixes
* print without tabulate
* fix pre-commits
* plot gnatt
* color bug fix
* read without timestampextra
* bump panda
* mono time instead of frame id
* finnish script
* clean unused
* clean unused logging
* monotonic + json fixes
* del test
* remove whilelines
* bump laika
* cleanup
* remove deps
* logs nicer strings
* remove plotting from scirpt
* reset pipfile
* reset pipfile
* nicer strings
* bug fix
* bug fix
* pr comments cleaning
* remove plotting
* bug fix
* new demo route
* bump opendbc and panda
* cereal master
* cereal master
* script less komplex
* assertions
* matplotlib
* readme
* Update README.md
* graph html
* design fixes
* more code design
* Update common/logging_extra.py
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* whitespace
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* Update tools/latency_logger/latency_logger.py
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* pr comments
* bug fix
* readme + env once
* clean swaglog
* bug fix
* Update tools/latencylogger/README.md
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
* revert
* revert
* clean swaglog with error
* remove typo file
* revert graph
* cereal
* submodules
* whitespaces
* update refs
Co-authored-by: Bruce Wayne <batman@workstation-openpilot2.internal>
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: Adeeb Shihadeh <adeebshihadeh@gmail.com>
4 years ago
de4031c98e
DM: more precision running on DSP + e2e outputs ( #23900 )
...
* 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
4 years ago
5c5a56c5e6
thneed: a more sane way of doing record/debug ( #23938 )
...
Co-authored-by: Comma Device <device@comma.ai>
4 years ago
492398826f
modeld: sync based on frame timestamp ( #23901 )
...
* sync based on frame ts
* log extra frame id
* ints only
* update ref
* no rounding errors
4 years ago
8d6f49aecf
model: mse err from 0.02-> 0.000056 ( #23891 )
...
* 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>
4 years ago
825c924c1c
minor cleanups, fix non binary compile ( #23882 )
...
Co-authored-by: Comma Device <device@comma.ai>
4 years ago
8a19d9892e
modeld: remove support for small model ( #23803 )
...
* modeld: remove support for small model
* use extra
4 years ago
83159a09bf
THNEED_DEBUG env var support
4 years ago
48154703a7
Fix tici bigmodel ( #23817 )
...
* 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
4 years ago
2b652605a0
thneed: a few asserts in the optimizer for cases it will fail
4 years ago
2c7542d34e
Refactor convolutions ( #23807 )
...
* one conv with defines
* add conv
* building works on C3
* this is num_outputs too, process replay is so useful
Co-authored-by: Comma Device <device@comma.ai>
4 years ago
Comma Device
ZwX1616
Willem Melching
George Hotz
Gijs Koning
Adeeb Shihadeh
HaraldSchafer
YassineYousfi
grekiki
Shane Smiskol
Lukas Petersson