mawei/StarPilot
1
0
Fork 0
mirror of https://github.com/firestar5683/StarPilot.git synced 2026-07-01 19:42:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

model parser: use check missing for mhp checks (#36020)

Browse Source 
* model parser: use check missing for mhp checks

* lint + support re

* lint...

* no walrus

* just remove
This commit is contained in:
YassineYousfi
2025-08-19 10:09:09 -07:00
committed by GitHub
parent c085b8af19
commit 803b54ebdb
2 changed files with 20 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
selfdrive/modeld/modeld.py
+1 -1
View File
@@ -116,7 +116,7 @@ class ModelState:
self.vision_output = np.zeros(vision_output_size, dtype=np.float32)
self.policy_inputs = {k: Tensor(v, device='NPY').realize() for k,v in self.numpy_inputs.items()}
self.policy_output = np.zeros(policy_output_size, dtype=np.float32)
self.parser = Parser()
self.parser = Parser(ignore_missing=('desired_curvature',))
with open(VISION_PKL_PATH, "rb") as f:
self.vision_run = pickle.load(f)
selfdrive/modeld/parse_model_outputs.py
+19 -16
View File
@@ -22,9 +22,10 @@ class Parser:
self.ignore_missing = ignore_missing
def check_missing(self, outs, name):
if name not in outs and not self.ignore_missing:
missing = name not in outs
if missing and not self.ignore_missing:
raise ValueError(f"Missing output {name}")
return name not in outs
return missing
def parse_categorical_crossentropy(self, name, outs, out_shape=None):
if self.check_missing(outs, name):
@@ -84,6 +85,13 @@ class Parser:
outs[name] = pred_mu_final.reshape(final_shape)
outs[name + '_stds'] = pred_std_final.reshape(final_shape)
def is_mhp(self, outs, name, shape):
if self.check_missing(outs, name):
return False
if outs[name].shape[1] == 2 * shape:
return False
return True
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,))
@@ -94,23 +102,18 @@ class Parser:
self.parse_categorical_crossentropy('desire_pred', outs, out_shape=(ModelConstants.DESIRE_PRED_LEN,ModelConstants.DESIRE_PRED_WIDTH))
self.parse_binary_crossentropy('meta', outs)
self.parse_binary_crossentropy('lead_prob', 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))
lead_mhp = self.is_mhp(outs, 'lead', ModelConstants.LEAD_MHP_SELECTION * ModelConstants.LEAD_TRAJ_LEN * ModelConstants.LEAD_WIDTH)
lead_in_N, lead_out_N = (ModelConstants.LEAD_MHP_N, ModelConstants.LEAD_MHP_SELECTION) if lead_mhp else (0, 0)
self.parse_mdn(
'lead', outs, in_N=lead_in_N, out_N=lead_out_N,
out_shape=(ModelConstants.LEAD_MHP_SELECTION, ModelConstants.LEAD_TRAJ_LEN, ModelConstants.LEAD_WIDTH)
)
return outs
def parse_policy_outputs(self, outs: dict[str, np.ndarray]) -> dict[str, np.ndarray]:
if outs['plan'].shape[1] == 2 * ModelConstants.IDX_N * ModelConstants.PLAN_WIDTH:
self.parse_mdn('plan', outs, in_N=0, out_N=0,
out_shape=(ModelConstants.IDX_N,ModelConstants.PLAN_WIDTH))
else:
self.parse_mdn('plan', outs, in_N=ModelConstants.PLAN_MHP_N, out_N=ModelConstants.PLAN_MHP_SELECTION,
out_shape=(ModelConstants.IDX_N,ModelConstants.PLAN_WIDTH))
if 'desired_curvature' in outs:
self.parse_mdn('desired_curvature', outs, in_N=0, out_N=0, out_shape=(ModelConstants.DESIRED_CURV_WIDTH,))
plan_mhp = self.is_mhp(outs, 'plan', 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))
self.parse_categorical_crossentropy('desire_state', outs, out_shape=(ModelConstants.DESIRE_PRED_WIDTH,))
return outs