* Refactor model runner methods for improved abstraction.
Moved slicing logic to a private `_slice_outputs` method and decoupled `_run_model` for clearer subclass implementation. Removed redundant `output` attribute in `ModelState` to streamline data handling.
* Add output parsing to model_runner and remove duplicate logic
Integrates an output parser directly into `model_runner` for streamlined inference and parsing. Removes redundant parser initialization from `modeld` to avoid duplication and enhance maintainability.
* Reordering
* linter
* linter
* Refactor model handling with `ModelData` abstraction
Introduce a `ModelData` class to encapsulate model and metadata logic, improving code clarity and modularity. Refactor `ModelRunner` to manage multiple models and add conditional handling for fallback scenarios. Adjust `TinygradRunner` to validate and use the new `ModelData` structure.
* Refactor model handling to use dictionary-based structure
Replaces the model list with a dictionary keyed by model type to improve clarity and maintainability. Updates related logic and ensures consistent handling of model metadata and inputs. Adds `slice_outputs` implementation to the `TinygradRunner` for proper output parsing.
* Refactor model runners to support policy and vision separation
Introduced `TinygradPolicyRunner`, `TinygradVisionRunner`, and `TinygradSplitRunner` to enable separate handling of policy and vision models. Updated `TinygradRunner` initialization and input preparation to accommodate modular processing. Adjusted `modeld` to utilize the new runners, ensuring compatibility with separated model workflows.
* Refactor model runner initialization and simplify logic
Introduce `get_model_runner` to centralize model runner selection logic, replacing multiple conditional instantiations. Simplify the handling of model metadata by removing fallback logic and restructuring output slicing to enforce proper loading of model data. These changes improve code maintainability and clarity.
* Refactor model data access for TinygradRunner initialization
Update references to access nested artifact properties and align with structural changes to the model data schema. This simplifies input shapes handling and ensures compatibility with updated model attributes.
* Refactor imports and clean up redundant code.
Removed unused imports and improved formatting for clarity and maintainability. These changes simplify the codebase by eliminating unnecessary dependencies and ensuring consistency.
* Refactor model output parsing with specialized parsers.
Introduce abstract `_parse_outputs` method to standardize parsing logic. Add `SplitParser` for specialized parsing in `TinygradVisionRunner` and `TinygradPolicyRunner`. This improves modularity and paves the way for easier parser customization.
* Add parser for model output processing in modeld_v2
Introduce a new `Parser` class to handle parsing and processing of model outputs, including MDN, binary cross-entropy, and categorical cross-entropy outputs. This modularizes the logic, improves clarity, and prepares for handling various types of model data.
* Add `input_shapes` property to model runners
Introduce a new `input_shapes` property in the abstract base class and its implementation in derived classes. This provides a standardized way to access the input shapes of models, improving clarity and consistency in the model runners.
* Refactor model runner to use private `_model_data` attribute
Replaced public `model_data` with private `_model_data` for improved encapsulation. Updated all references and property accessors accordingly. Simplified model type handling by using raw types where applicable.
* Remove debug print statement from model_runner.py
The unnecessary `print(model_type)` statement was removed as it served no functional purpose in the code. This improves code cleanliness and avoids unintended console output during execution.
* Refactor `_parse_outputs` call in `run_model`.
Replaced the use of `self.parser.parse_outputs` with `self._parse_outputs` for clarity and consistency. Updated method signature to align with the revised usage.
* Refactor model output parsing for clarity and scope separation
Moved specific parsing logic (e.g., lane_lines, lead) from `parse_model_outputs` to `parse_policy_outputs` to better align with functional responsibilities. This improves modularity and readability while maintaining existing functionality.
* Refactor model_runner to simplify result handling
Renamed variable `result` to `parsed_result` for clarity and removed unnecessary slicing during model output parsing. These changes improve code readability and maintain consistency within the `run_model` method.
* Adjust _parse_outputs method signature in model_runner
Updated the method signature of _parse_outputs to accept a single np.ndarray instead of a dictionary. This aligns with the intended data structure and ensures consistency across subclasses implementing this abstract method.
* Refactor ModelRunner to enforce abstract base class compliance
Updated `ModelRunner` and its subclasses to properly inherit from `ABC` while refactoring methods to ensure compliance with Python's abstract base class standards. Streamlined the handling of `_parse_outputs` and added a new `input_shapes` property for improved functionality.
* Fix buffer length issue in 20Hz model initialization
Adjusted `FULL_HISTORY_BUFFER_LEN` by adding +1 for `full_features_20Hz` to address compatibility issues with the current FoF model. Added a comment noting potential failure for other models with this adjustment.
* Refactor TinygradRunner to remove abstract methods.
Simplified the TinygradRunner class by removing unnecessary @abstractmethod decorators and redundant method definitions. This streamlines the code and aligns it more effectively with its current usage and implementation.
* Refactor model runner classes and enhance type annotations
Simplified model runner implementations, added type annotations, and improved code readability and maintainability. Introduced new type definitions, updated metadata handling, and standardized input/output parsing across all runner classes. Minor comment update in `modeld.py` for clarity.
* Refactor model runner classes with detailed docstrings.
Enhanced class and function docstrings across model_runner.py for better clarity and maintainability. Descriptions now include detailed explanations of attributes, purposes, and workflows to aid understanding and future development.
* Refactor model runner classes and add TICI hardware optimization
Simplified and clarified class definitions, comments, and functionality for ModelRunner subclasses. Introduced the use of QCOM environment variable on TICI for potential hardware acceleration. Enhanced input/output handling and error reporting across Tinygrad and ONNX implementations.
* Update parser import and usage to use CombinedParser
Replaced the Parser class with CombinedParser in model_runner.py. This change ensures consistency with the updated parsing logic, aligning with the latest requirements for combined model output handling.
* Refactor TinygradRunner hierarchy for modular parsers
Reorganized the TinygradRunner and its specialized runners (Vision, Policy, and Supercombo) into a cleaner, modular structure using composable classes. This consolidates parser logic, removes redundancy, and simplifies initialization by leveraging a shared base class with a dictionary-based parser method.
* Refactor model runners to use ModularRunner as abstract base.
Introduce a new `ModularRunner` class to enforce a consistent interface across model runners. Updated existing runners, including `ModelRunner`, `SupercomboTinygrad`, `PolicyTinygrad`, and `VisionTinygrad`, to extend `ModularRunner`. Added abstract methods and properties to enhance modularity and code maintainability.
* Refactor model runners into modular components.
This commit separates the logic for Tinygrad, ONNX, and split runners into clearly defined modules and components. It introduces `PolicyTinygrad`, `VisionTinygrad`, `SupercomboTinygrad`, and centralized helpers for cleaner architecture. The changes improve modularity and maintainability of the model running and parsing workflows.
* Simplify imports and clean up unused code in ONNXRunner.
Removed unused imports and redundant environmental variables to streamline the codebase. Consolidated necessary imports and organized type definitions for improved readability and maintenance.
* Standardize imports and add model data validation.
Updated import paths to ensure consistency across modules by using `openpilot` as the base. Introduced validation in `_parse_outputs` methods to handle cases where `_model_data` is not initialized, preventing potential runtime errors.
* Remove unused import and fix whitespace in runners
The unused import `ModelData` was removed from `tinygrad_runner.py` to clean up the code. Additionally, extraneous whitespace was corrected in `onnx_runner.py` for improved readability and consistency.
* Remove unnecessary blank line in import statements
Cleaned up import section by removing an extra blank line. This helps maintain consistency and adheres to code style conventions.
* BROKEN!! Staging code but its not gonna work. Also I realized we need to run the split models in 2 stages because the output of one is immediately needed for the input of the other. We might handle it inside of the model_runner instead
* update smooth
* Revert "update smooth"
This reverts commit c335712e6e1ee189459ce34dfc9d4028feb9470f.
* match case made this very hard to read.
* shouldnt be there
* Refactor to allow TR (soon TM)
* TR 7 is .1
* metadata
* .2=3
* Remove redundant comments and clean up conditional blocks in modeld.py.
* Undoing wrong buffer
* Refactor model initialization and adjust ONNX runner import
Reorganized numpy input buffer initialization and updated `temporal_idxs` logic for better clarity and efficiency. Conditional import for ONNXRunner added for non-TICI platforms to optimize imports. These changes improve maintainability and compatibility across platforms.
* Update CURRENT_SELECTOR_VERSION to 4
Bump the CURRENT_SELECTOR_VERSION constant from 3 to 4 to reflect changes in the selector logic or requirements. This ensures compatibility with the updated selector version while maintaining the minimum required version as 2.
* Add output_slices property to model runners
Introduce output_slices property to provide access to the output slices for individual and combined models. This ensures consistent handling of output slices across vision and policy models, improving modularity and usability.
* Refactor imports to use SplitModelConstants consistently
Updated import references to use the renamed `SplitModelConstants` class for consistency across files. This change ensures clarity and better alignment with the updated class naming convention.
* Refactor buffer initialization and desired curvature handling
Refactored model input buffer initialization for improved clarity and consistency, leveraging dynamic shape calculations. Extracted `process_desired_curvature` method to encapsulate logic for handling 3D and non-3D cases. Simplified temporal index generation and related calculations for better maintainability.
* Refactor desire reshape dims logic in modeld.py
Adjust logic for setting desire reshape dimensions to handle `is_20hz_3d` separately. This improves clarity and ensures proper handling of different model runner configurations.
* Fix off-by-one error in full_desire buffer initialization
The full_desire buffer length was mistakenly set to full_history_buffer_len + 1. This change corrects it to match the intended full_history_buffer_len, ensuring proper alignment with other buffers.
* Simplify desire reshape logic by removing unused condition.
Removed the `is_20hz_3d` condition and associated reshape logic since it is no longer needed. This streamlines the code and avoids unnecessary checks for unused configurations.
* Refactor buffer initialization for 20Hz model variants
Reorganized buffer initialization logic to prioritize the 20Hz_3D condition. This improves clarity and ensures specific handling of different 20Hz configurations. Adjusted the order of conditions to streamline execution flow.
* Refactor: Move `get_action_from_model` and constants to `Model` class to improve encapsulation and readability.
* 12 line reshaping red diff
* .2 to match old models delay
* mypy fixes
* Revert "12 line reshaping red diff"
This reverts commit 8c7280f629043f0485749e2536a20af74c9209b2.
* mypy
* remove this
* Fix desired curvature for models which do not output desired_curvature
* fix FoF
* flip policy and vision outs to allow FoF and tomb raider to live in harmony using conditional `if 'this' in outs:'`
* noqa
* single
* sunnypilot modeld.py
* action
* overrides methodology
* combine split outputs to its own method
* comments
* Fix static checker line length
* static will fail on line length
lines:
286,
206,
70 - 77,
159,
168
* Address E501 line length violations
* This will make TR better while not effecting FoF/VFF at all
* Reduce this to one conditional and just call normally in vision/policy
* Align with upstream in our own way.
* check for desired curvature in outputs first
* outputs
* Use a cleaner import method
* Fix output
* Clean up some values
* Only call on init
* slight cleanup
* names!!!!!!!!!
* Refactor overrides structure to support key-value pairs.
The overrides structure now uses a list of key-value pairs instead of fixed lat/long fields. This change improves flexibility, allowing dynamic addition of override parameters. Code adjustments ensure backward compatibility and consistent behavior throughout the application.
* Refactor: Use local variable for SplitModelConstants
Introduce a local `constants` variable to replace repeated access to `SplitModelConstants`. This simplifies code readability and adheres to linter recommendations for line length.
* Refactor model constant handling to improve modularity
Replaced direct usage of model constants with dynamic access through model runners for better scalability and maintainability. This change centralizes constant definitions, reduces redundancy, and ensures clearer integration with different model types.
---------
Co-authored-by: discountchubbs <alexgrant990@gmail.com>
Co-authored-by: Discountchubbs <159560811+Discountchubbs@users.noreply.github.com>
Co-authored-by: Jason Wen <haibin.wen3@gmail.com>
* Fixes an issue on the long planner since Tomb Raider models, where the models are now meant to output the acceleration target and the "should stop" instead of it being calculated. However, older models (particularly those running on modeld_v2 from SP) do not output this. Leading to a "coasting" situation instead of braking when only e2e is used which is totally wrong.
* init dec
* Update sunnypilot/selfdrive/controls/lib/dynamic_experimental_controller.py
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
* Update sunnypilot/selfdrive/controls/lib/dynamic_experimental_controller.py
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
* fix static test
* ff
* fix static test
* unitee testt
* Refactor test_dynamic_controller and fix formatting issues
Added a new import for STOP_AND_GO_FRAME and corrected a float initialization for v_ego in MockCarState. Also fixed indentation in the test_standstill_detection method for consistency.
* Refactor test indentation for dynamic controller tests
Adjust indentation and formatting in test_dynamic_controller.py to ensure consistency and readability. This change does not alter functionality but improves the maintainability of the test code.
* Migrated to pytest using claude
* Integrate radar parameter into dynamic controller's pytest tests
Added a `has_radar` parameter to the test functions in the dynamic controller's pytest file. This allows each function to run both with and without radar inputs, thus enhancing the coverage of our test cases.
* Disabling unittest file to allow checks on the pipeline to succeed.
Pending to remove this, but leaving it to validate the move to pytest is okay before merging
* Replace unittest with pytest for dynamic controller tests
Migrated dynamic controller tests from unittest to pytest for improved readability and maintainability. Refactored mock setup using pytest fixtures and monkeypatching while preserving test coverage.
* new line...
* Refactor and modularize DynamicExperimentalController logic
Moved DynamicExperimentalController logic and helper functions to a dedicated module for better readability and maintainability. Simplified longitudinal planner logic by introducing reusable methods to manage MPC mode and longitudinal plan publishing. Adjusted file structure for dynamic controller-related components and updated relevant imports.
* Add missing import for messaging in helpers.py
The `messaging` module was added to resolve potential issues with undefined references. This change ensures all required imports are present, improving the reliability and maintainability of the code.
* Format
* Formatting
* rebase fix
* Refactor MpcSource definition and update references.
Moved MpcSource enum into LongitudinalPlanSP for better encapsulation. Updated references in helpers.py to use the new path. This change improves code organization and maintains functionality.
* Format
* Refactor DEC into a dedicated longitudinal planner class
Move Dynamic Experimental Control (DEC) logic to a new `DecLongitudinalPlanner` class for better modularity and maintainability. This simplifies the `LongitudinalPlanner` by delegating DEC-specific behavior and consolidates related methods into a single file. Additionally, redundant code was removed to improve readability and reduce complexity.
* **Refactor DEC module structure for better organization**
Moved DEC-related files from `dec` to `lib` for improved clarity and consistency within the project structure. Updated all relevant import paths to reflect the new locations. Ensured functionality remains unaffected with these changes.
* static test
* static
* had moved to car_state
* cleanup
* some more
* static method
* move around
* more cleanup
* stuff
* into their own
* rename
* check live param
* sync with stock
* type hint
* unused
* smoother trans
* window time
* fix type hint
* pass sm.frame from plannerd
* more fixes
* more
* more explicit
* fix test
* Revert "fix test"
This reverts commit 635b15f2bc11a8ddd5c4194546d51df33de324a0.
* Revert "pass sm.frame from plannerd"
This reverts commit a8deaa69b89f599f86ae517827a570789566e079.
* use internal frame
* update name
* never used
* this is why it was never using DEC
* more logs
* slight cleanup
* remove to fail test
* update name
* more
* rename
* move around
* explicit type hints
* move to constants py
* Revert "explicit type hints"
This reverts commit c205497b
* more
* don't set to exp mode initial if DEC is active
* use walrus for None
* Revert "use walrus for None"
This reverts commit 5f2396d490deded87d43e378bd9e74738fe307b0.
* fix wrong typing and variable name
* use walrus (needs cleanup)
* fix tests
* revert smooht lead for now
* dec: how good is FirstOrderFilter?
* Update dec.py
* dec: faster ?
* Revert "dec: faster ?"
This reverts commit 40259cd22ad23d01e63a9faa47a0cf0edcc73399.
* Revert "Update dec.py"
This reverts commit 3f29ccbd99c538e9f3d11c6178bc90b0a2ed3f7b.
* Revert "dec: how good is FirstOrderFilter?"
This reverts commit 01e06df542894b468fb9460c60bca1b09bed4eec.
* Update slow-down logic and constants for improved behavior
Adjust the slowdown scaling factor and anomaly handling to refine behavior without abrupt resets. Modify constants to increase window size and adjust probabilities and distances for smoother adaptation. Update version to reflect the new changes.
* Fix lead detection fallback for weighted average check.
Add a fallback value of -1 when computing the weighted average to prevent errors caused by invalid or None values. This ensures robust lead detection and avoids potential crashes or undefined behavior.
* visuals for DEC
* try this
* add opacity
* should be active and dimmer
* even dimmer
* Update dec.py
* Update constants.py
* use another method for drawing
* migrate to sp only
* fix
* init
---------
Co-authored-by: rav4kumar <meetkumardesai@gmail.com>
Co-authored-by: Kumar <36933347+rav4kumar@users.noreply.github.com>
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
Co-authored-by: DevTekVE <devtekve@gmail.com>
* Misc fixes
* don't check allow_throttle slowdown for e2e
* Removed unused variable
* believe this clip is still necessary
* Update process replay refs
---------
Co-authored-by: Bruce Wayne <harald.the.engineer@gmail.com>
* long planner: use vehicle model w/ avg steer offset for limit accel in turns
* remove unused CP in limit_accel_in_turns
* revert use of vehicle model, keeping angle offset in limit accel in turns
* only the offset fix, check valid, and fix process replay
* update refs (valid two frames later)
---------
Co-authored-by: Shane Smiskol <shane@smiskol.com>
* Deprecate controlsState state fields
* sim works
* update refs
* one more
* these too
* update sim
old-commit-hash: 3924ac587b735d1e735af4cb77faf6ccf053f656
* Move vCruise to card
* cleanup drive_helpers
* works in sim
* update refs
* update that
* too slow :(
old-commit-hash: 2f3256ed8baa3d7a5c4d1befe9148dbfecb37246
* move most of /car
* move some car tests
move some car tests
* fix selfdrive/car/tests
* fix selfdrive/controls tests
* fix the rest of the selfdrive tests
* bump opendbc
* fix all tests
* few more non-test references
* remove opcar and move docs to car
fix these debugging scripts
fix docs
* bump opendbc and panda
forgot panda
old-commit-hash: e735a7f3796e208cdc1ecc651ace09e1daf6009a
* Simplify long control
* Seperate
* Rename
* Try new api for toyota
* rm v_pid everywhere
* No speed in reset
* 0 is better default
* unassigned variable
* Update other cars
* Update gm
* SIMPLIFY
* simplify more
* fix API boundry
* Fix stopping bug
* Small fixes
* Update ref
old-commit-hash: bc303df6a0a4a9d52a2e92e5976b6c7aa5138b95
* start at param
* start by sending personality
* change to personality
* POC: button changes personality
* what's wrong with this?
* fix
* not really possible but fuzzy test catches this
* there's always a typo
* dang, we're dropping messages
* clean up
* no comment
* bump
* rename
* not all cars yet
* works but at what cost
* clean up
* inside settings
* write param so we save the distance button changes
* setChecked activates buttonToggled and already writes param!
* don't need this, we update from longitudinalPlan on changes
* some clean up
* more
* ui
* allow some time for ui to receive and write param
* plannerd: only track changes in case no ui
* Revert "plannerd: only track changes in case no ui"
This reverts commit 2b081aa6ceb92c67a621b74592b2292756d29871.
* write in plannerd as well, I assume this is atomic?
* don't write when setting checked (only user clicks)
* better nane
* more
* Update selfdrive/controls/lib/longitudinal_planner.py
Co-authored-by: Cameron Clough <cameronjclough@gmail.com>
* doesn't write param now
* ParamWatcher is nice
* no debug
* Update translations
* fix
* odd drain sock proc replay behavior
* vanish
* Revert "odd drain sock proc replay behavior"
This reverts commit 29b70b39413e1852bb512155af6b6a94a5bd9454.
* add GM
* only if OP long
* move personality to controlsState, since eventually it won't be exclusive to long planner
more
bump
* diff without translations
* fix
* put nonblocking
* CS should start at up to date personality always (no ui flicker)
* update toggle on cereal message change
* fix
* fix that
* ubmp
* mypy doesn't know this is an int :(
* update translations
* fix the tests
* revert ui
* not here
* migrate controlsState
* Revert "migrate controlsState" - i see no reason we need to test with
any specific personality
This reverts commit 6063508f2df1a5623f113cda34dcd59a1f4b2ac9.
* Update ref_commit
---------
Co-authored-by: Cameron Clough <cameronjclough@gmail.com>
old-commit-hash: 29e55f99a54d95215aa79ecf94a22363f82913a6
* 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: cad17b125595c4654bfd8299b041b94ccb3faf73
* first draft copy, needs updates
* gate behind exp mode
* can be one line
* this is no longer true
* toggle isn't just e2e long now, rename
* don't enable/disable
* kinda works!
* remove old giant qstring
* comment clean up
* similar breakpoint
* more clean up
* fixup onroad
* preserve planner behavior, and we don't need to look at confirmed param if we're onroad
* update translations
* vanish translations
* use scene for op long
* lowercase!
* updated copy
* need to check longitudinal here now too
* clean up!
* here is better
* used
* no nav emoji
* don't check param if not valid
* revert this
revert this
* ed
old-commit-hash: f973d605b2121a575a46f4a18dfcbb2df1f4816b
infiniteCable2