mirror of
https://github.com/firestar5683/StarPilot.git
synced 2026-11-08 13:33:42 +08:00
firestar5683
2818bb072e
Own model discovery, compilation and registry selection through explicit model metadata and geometry contracts.
88 lines
5.5 KiB
Python
88 lines
5.5 KiB
Python
"""Output parsing for the v8–v16 model catalog; bundled parsing stays upstream."""
|
||
|
||
import numpy as np
|
||
from openpilot.selfdrive.modeld.constants import ModelConstants
|
||
from openpilot.selfdrive.modeld.parse_model_outputs import Parser as CurrentParser
|
||
|
||
|
||
class Parser(CurrentParser):
|
||
def split_outputs(self, outs: dict[str, np.ndarray]) -> None:
|
||
if 'lead' in outs:
|
||
if outs['lead'].shape[1] == 2 * ModelConstants.LEAD_MHP_SELECTION * ModelConstants.LEAD_TRAJ_LEN * ModelConstants.LEAD_WIDTH:
|
||
self.parse_mdn('lead', outs, in_N=0, out_N=0,
|
||
out_shape=(ModelConstants.LEAD_MHP_SELECTION, ModelConstants.LEAD_TRAJ_LEN, ModelConstants.LEAD_WIDTH))
|
||
else:
|
||
self.parse_mdn('lead', outs, in_N=ModelConstants.LEAD_MHP_N, out_N=ModelConstants.LEAD_MHP_SELECTION,
|
||
out_shape=(ModelConstants.LEAD_TRAJ_LEN, ModelConstants.LEAD_WIDTH))
|
||
if 'plan' in outs:
|
||
plan_mhp = outs['plan'].shape[1] != 2 * ModelConstants.IDX_N * ModelConstants.PLAN_WIDTH
|
||
plan_in_N, plan_out_N = (ModelConstants.PLAN_MHP_N, ModelConstants.PLAN_MHP_SELECTION) if plan_mhp else (0, 0)
|
||
self.parse_mdn('plan', outs, in_N=plan_in_N, out_N=plan_out_N,
|
||
out_shape=(ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH))
|
||
if 'planplus' in outs:
|
||
self.parse_mdn('planplus', outs, in_N=plan_in_N, out_N=plan_out_N, out_shape=(ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH))
|
||
elif 'planplus' in outs:
|
||
planplus_mhp = outs['planplus'].shape[1] != 2 * ModelConstants.IDX_N * ModelConstants.PLAN_WIDTH
|
||
planplus_in_N, planplus_out_N = (ModelConstants.PLAN_MHP_N, ModelConstants.PLAN_MHP_SELECTION) if planplus_mhp else (0, 0)
|
||
self.parse_mdn('planplus', outs, in_N=planplus_in_N, out_N=planplus_out_N, out_shape=(ModelConstants.IDX_N, ModelConstants.PLAN_WIDTH))
|
||
if 'lane_lines' in outs:
|
||
self.parse_mdn('lane_lines', outs, in_N=0, out_N=0,
|
||
out_shape=(ModelConstants.NUM_LANE_LINES, ModelConstants.IDX_N, ModelConstants.LANE_LINES_WIDTH))
|
||
if 'road_edges' in outs:
|
||
self.parse_mdn('road_edges', outs, in_N=0, out_N=0,
|
||
out_shape=(ModelConstants.NUM_ROAD_EDGES, ModelConstants.IDX_N, ModelConstants.LANE_LINES_WIDTH))
|
||
if 'sim_pose' in outs:
|
||
self.parse_mdn('sim_pose', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
|
||
if 'lane_lines_prob' in outs:
|
||
self.parse_binary_crossentropy('lane_lines_prob', outs)
|
||
if 'lead_prob' in outs:
|
||
self.parse_binary_crossentropy('lead_prob', outs)
|
||
|
||
def parse_off_policy_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
|
||
self.split_outputs(outs)
|
||
if 'desire_state' in outs:
|
||
self.parse_categorical_crossentropy('desire_state', outs, out_shape=(ModelConstants.DESIRE_PRED_WIDTH,))
|
||
return outs
|
||
|
||
def parse_vision_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
|
||
self.parse_mdn('pose', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
|
||
self.parse_mdn('wide_from_device_euler', outs, in_N=0, out_N=0, out_shape=(ModelConstants.WIDE_FROM_DEVICE_WIDTH,))
|
||
self.parse_mdn('road_transform', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
|
||
self.split_outputs(outs)
|
||
self.parse_categorical_crossentropy('desire_pred', outs, out_shape=(ModelConstants.DESIRE_PRED_LEN, ModelConstants.DESIRE_PRED_WIDTH))
|
||
self.parse_binary_crossentropy('meta', outs)
|
||
return outs
|
||
|
||
def parse_policy_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
|
||
self.split_outputs(outs)
|
||
if 'action' in outs:
|
||
self.parse_mdn('action', outs, in_N=0, out_N=0, out_shape=(ModelConstants.ACTION_WIDTH,))
|
||
if 'lat_planner_solution' in outs:
|
||
self.parse_mdn('lat_planner_solution', outs, in_N=0, out_N=0, out_shape=(ModelConstants.IDX_N, ModelConstants.LAT_PLANNER_SOLUTION_WIDTH))
|
||
if 'desired_curvature' in outs:
|
||
self.parse_mdn('desired_curvature', outs, in_N=0, out_N=0, out_shape=(ModelConstants.DESIRED_CURV_WIDTH,))
|
||
if 'desire_state' in outs:
|
||
self.parse_categorical_crossentropy('desire_state', outs, out_shape=(ModelConstants.DESIRE_PRED_WIDTH,))
|
||
return outs
|
||
|
||
def parse_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
|
||
# Combined supercombo outputs contain both vision and policy slices in the
|
||
# same dictionary. Parse shared MDN outputs once; the split runtime keeps
|
||
# using parse_vision_outputs/parse_policy_outputs independently.
|
||
self.parse_mdn('pose', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
|
||
self.parse_mdn('wide_from_device_euler', outs, in_N=0, out_N=0, out_shape=(ModelConstants.WIDE_FROM_DEVICE_WIDTH,))
|
||
self.parse_mdn('road_transform', outs, in_N=0, out_N=0, out_shape=(ModelConstants.POSE_WIDTH,))
|
||
self.split_outputs(outs)
|
||
self.parse_categorical_crossentropy('desire_pred', outs, out_shape=(ModelConstants.DESIRE_PRED_LEN, ModelConstants.DESIRE_PRED_WIDTH))
|
||
self.parse_binary_crossentropy('meta', outs)
|
||
if 'action' in outs:
|
||
self.parse_mdn('action', outs, in_N=0, out_N=0, out_shape=(ModelConstants.ACTION_WIDTH,))
|
||
if 'lat_planner_solution' in outs:
|
||
self.parse_mdn('lat_planner_solution', outs, in_N=0, out_N=0,
|
||
out_shape=(ModelConstants.IDX_N, ModelConstants.LAT_PLANNER_SOLUTION_WIDTH))
|
||
if 'desired_curvature' in outs:
|
||
self.parse_mdn('desired_curvature', outs, in_N=0, out_N=0, out_shape=(ModelConstants.DESIRED_CURV_WIDTH,))
|
||
if 'desire_state' in outs:
|
||
self.parse_categorical_crossentropy('desire_state', outs, out_shape=(ModelConstants.DESIRE_PRED_WIDTH,))
|
||
return outs
|