mirror of
https://github.com/sunnypilot/sunnypilot.git
synced 2026-07-23 05:42:07 +08:00
ZwX1616
02f0f39b52
* get log
* simplify two nonsense
* not needed
* libyuv is a joke
* clean up
* try small
* fast but not bad
* working
* clean up driverview
* simplified
* thats mirrored
* smol
* tweak
* ref is screen
* w/ ee
* update camera model
* no if TICI
* start
* update pose thresh
* less cpu more dsp
* new libyuv
* new snpe
* add files
* test
* should be fast
* update out len
* trigger test
* use master snpe
* add cereal
* update cereal
* refactor parsing
* missing ;
* get
* wrong type
* test model
* use driver data
* 10829278-72fe-4283-a118-2cef959ce174/1550
* no pf
* adapt driverview
* ;
* rhd learner
* update libyuv buildi x64
* ad4337ea
* remove blink slack
* test
* no
* use toggle
* b16
* fix for nv12
* 5b02cff5 both
* update test
* update cereal
* update cereal
* update cereal
* v2 packets
* revert libyuv
* no /
* update snpemodel
* ;
* memcpy
* fix test
* use toggle in driverview
* update power
* update replay
* Revert "update replay"
This reverts commit 1d0979ca59dbc89bc5890656e9501e83f0556d50.
* update model ref
* halve cpu
* fake 8bit onnx runner
* same thresh as report
* cereal master
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: d6c07a6b15
Neural networks in openpilot
To view the architecture of the ONNX networks, you can use netron
Supercombo
Supercombo input format (Full size: 393738 x float32)
- image stream
- Two consecutive images (256 * 512 * 3 in RGB) recorded at 20 Hz : 393216 = 2 * 6 * 128 * 256
- Each 256 * 512 image is represented in YUV420 with 6 channels : 6 * 128 * 256
- Channels 0,1,2,3 represent the full-res Y channel and are represented in numpy as Y[::2, ::2], Y[::2, 1::2], Y[1::2, ::2], and Y[1::2, 1::2]
- Channel 4 represents the half-res U channel
- Channel 5 represents the half-res V channel
- Each 256 * 512 image is represented in YUV420 with 6 channels : 6 * 128 * 256
- Two consecutive images (256 * 512 * 3 in RGB) recorded at 20 Hz : 393216 = 2 * 6 * 128 * 256
- wide image stream
- Two consecutive images (256 * 512 * 3 in RGB) recorded at 20 Hz : 393216 = 2 * 6 * 128 * 256
- Each 256 * 512 image is represented in YUV420 with 6 channels : 6 * 128 * 256
- Channels 0,1,2,3 represent the full-res Y channel and are represented in numpy as Y[::2, ::2], Y[::2, 1::2], Y[1::2, ::2], and Y[1::2, 1::2]
- Channel 4 represents the half-res U channel
- Channel 5 represents the half-res V channel
- Each 256 * 512 image is represented in YUV420 with 6 channels : 6 * 128 * 256
- Two consecutive images (256 * 512 * 3 in RGB) recorded at 20 Hz : 393216 = 2 * 6 * 128 * 256
- desire
- one-hot encoded vector to command model to execute certain actions, bit only needs to be sent for 1 frame : 8
- traffic convention
- one-hot encoded vector to tell model whether traffic is right-hand or left-hand traffic : 2
- recurrent state
- The recurrent state vector that is fed back into the GRU for temporal context : 512
Supercombo output format (Full size: XXX x float32)
Read here for more.
Driver Monitoring Model
- .onnx model can be run with onnx runtimes
- .dlc file is a pre-quantized model and only runs on qualcomm DSPs
input format
- single image (640 * 320 * 3 in RGB):
- full input size is 6 * 640/2 * 320/2 = 307200
- represented in YUV420 with 6 channels:
- Channels 0,1,2,3 represent the full-res Y channel and are represented in numpy as Y[::2, ::2], Y[::2, 1::2], Y[1::2, ::2], and Y[1::2, 1::2]
- Channel 4 represents the half-res U channel
- Channel 5 represents the half-res V channel
- normalized, ranging from -1.0 to 1.0
output format
- 39 x float32 outputs (parsing example)
- face pose: 12 = 6 + 6
- face orientation [pitch, yaw, roll] in camera frame: 3
- face position [dx, dy] relative to image center: 2
- normalized face size: 1
- standard deviations for above outputs: 6
- face visible probability: 1
- eyes: 20 = (8 + 1) + (8 + 1) + 1 + 1
- eye position and size, and their standard deviations: 8
- eye visible probability: 1
- eye closed probability: 1
- wearing sunglasses probability: 1
- poor camera vision probability: 1
- face partially out-of-frame probability: 1
- (deprecated) distracted probabilities: 2
- face covered probability: 1
- face pose: 12 = 6 + 6