426 lines
18 KiB
Python
426 lines
18 KiB
Python
"""Validated, causal pooled and frame-set local-feature sidecars.
|
|
|
|
No model/decoder imports: these utilities are also used by CPU head training.
|
|
Sidecars store encoder-native vectors, never a randomly initialized projection.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
import math
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import torch
|
|
|
|
LOCAL_FORMAT = "qwen-local-pooled-v1"
|
|
MODALITIES = {"visual": ("visual",), "audio": ("audio",), "av": ("visual", "audio")}
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class FramePersonFeatures:
|
|
"""Ragged person sets indexed by aligned 5 Hz rows without frame duplication."""
|
|
|
|
features: torch.Tensor
|
|
frame_offsets: torch.LongTensor
|
|
row_to_frame: torch.LongTensor
|
|
chosen_frame_times: torch.Tensor
|
|
|
|
def __post_init__(self) -> None:
|
|
if (
|
|
not isinstance(self.features, torch.Tensor)
|
|
or self.features.ndim != 2
|
|
or not self.features.is_floating_point()
|
|
or not torch.isfinite(self.features).all()
|
|
or self.features.shape[1] <= 0
|
|
):
|
|
raise ValueError("Person features must be finite floating [N,D]")
|
|
if (
|
|
not isinstance(self.frame_offsets, torch.Tensor)
|
|
or self.frame_offsets.dtype != torch.long
|
|
or self.frame_offsets.ndim != 1
|
|
or not len(self.frame_offsets)
|
|
or int(self.frame_offsets[0]) != 0
|
|
or int(self.frame_offsets[-1]) != len(self.features)
|
|
or bool((self.frame_offsets[1:] < self.frame_offsets[:-1]).any())
|
|
):
|
|
raise ValueError("Invalid person frame_offsets")
|
|
if (
|
|
not isinstance(self.row_to_frame, torch.Tensor)
|
|
or self.row_to_frame.dtype != torch.long
|
|
or self.row_to_frame.ndim != 1
|
|
):
|
|
raise ValueError("row_to_frame must be int64 [T]")
|
|
num_frames = len(self.frame_offsets) - 1
|
|
if bool(((self.row_to_frame < -1) | (self.row_to_frame >= num_frames)).any()):
|
|
raise ValueError("row_to_frame contains an invalid frame index")
|
|
if (
|
|
not isinstance(self.chosen_frame_times, torch.Tensor)
|
|
or self.chosen_frame_times.dtype != torch.float64
|
|
or self.chosen_frame_times.shape != self.row_to_frame.shape
|
|
):
|
|
raise ValueError("chosen_frame_times must be float64 [T]")
|
|
missing = self.row_to_frame < 0
|
|
if not torch.equal(torch.isnan(self.chosen_frame_times), missing):
|
|
raise ValueError("Only rows without an available frame may have NaN frame time")
|
|
if not torch.isfinite(self.chosen_frame_times[~missing]).all():
|
|
raise ValueError("Chosen person frame times must be finite")
|
|
|
|
def __len__(self) -> int:
|
|
return len(self.row_to_frame)
|
|
|
|
@property
|
|
def dimension(self) -> int:
|
|
return int(self.features.shape[1])
|
|
|
|
@property
|
|
def max_people(self) -> int:
|
|
counts = self.frame_offsets[1:] - self.frame_offsets[:-1]
|
|
return int(counts.max()) if len(counts) else 0
|
|
|
|
def select_rows(self, indices: torch.Tensor) -> "FramePersonFeatures":
|
|
indices = torch.as_tensor(indices)
|
|
if indices.dtype != torch.long or indices.ndim != 1:
|
|
raise ValueError("Person row selection must be int64 [N]")
|
|
if len(indices) and (int(indices.min()) < 0 or int(indices.max()) >= len(self)):
|
|
raise IndexError("Person row selection is out of range")
|
|
return FramePersonFeatures(
|
|
self.features,
|
|
self.frame_offsets,
|
|
self.row_to_frame[indices],
|
|
self.chosen_frame_times[indices],
|
|
)
|
|
|
|
def padded(
|
|
self,
|
|
row_indices: torch.Tensor | None = None,
|
|
) -> tuple[torch.Tensor, torch.BoolTensor]:
|
|
"""Materialize only one batch as [B,P,D] plus a True-for-real mask."""
|
|
|
|
if row_indices is None:
|
|
frames = self.row_to_frame
|
|
else:
|
|
row_indices = torch.as_tensor(row_indices)
|
|
if row_indices.dtype != torch.long or row_indices.ndim != 1:
|
|
raise ValueError("Batch row indices must be int64 [B]")
|
|
if len(row_indices) and (
|
|
int(row_indices.min()) < 0 or int(row_indices.max()) >= len(self)
|
|
):
|
|
raise IndexError("Batch person row index is out of range")
|
|
frames = self.row_to_frame[row_indices]
|
|
valid_frames = frames >= 0
|
|
safe_frames = frames.clamp_min(0)
|
|
starts = torch.zeros_like(frames)
|
|
counts = torch.zeros_like(frames)
|
|
if bool(valid_frames.any()):
|
|
starts[valid_frames] = self.frame_offsets[safe_frames[valid_frames]]
|
|
counts[valid_frames] = (
|
|
self.frame_offsets[safe_frames[valid_frames] + 1]
|
|
- starts[valid_frames]
|
|
)
|
|
width = int(counts.max()) if len(counts) else 0
|
|
mask = torch.arange(width)[None, :] < counts[:, None]
|
|
if width == 0:
|
|
return self.features.new_zeros((len(frames), 0, self.dimension)), mask
|
|
person_indices = starts[:, None] + torch.arange(width)[None, :]
|
|
safe_indices = person_indices.masked_fill(~mask, 0)
|
|
values = self.features[safe_indices]
|
|
return values.masked_fill(~mask[..., None], 0), mask
|
|
|
|
@classmethod
|
|
def concatenate(
|
|
cls,
|
|
parts: list["FramePersonFeatures"],
|
|
) -> "FramePersonFeatures":
|
|
if not parts:
|
|
raise ValueError("Cannot concatenate no person feature sets")
|
|
dimension = parts[0].dimension
|
|
if any(part.dimension != dimension for part in parts):
|
|
raise ValueError("Person feature dimensions differ across sessions")
|
|
feature_parts = []
|
|
offset_parts = [torch.zeros(1, dtype=torch.long)]
|
|
row_parts = []
|
|
time_parts = []
|
|
feature_base = 0
|
|
frame_base = 0
|
|
for part in parts:
|
|
feature_parts.append(part.features)
|
|
offset_parts.append(part.frame_offsets[1:] + feature_base)
|
|
rows = part.row_to_frame.clone()
|
|
valid = rows >= 0
|
|
rows[valid] += frame_base
|
|
row_parts.append(rows)
|
|
time_parts.append(part.chosen_frame_times)
|
|
feature_base += len(part.features)
|
|
frame_base += len(part.frame_offsets) - 1
|
|
return cls(
|
|
torch.cat(feature_parts, dim=0),
|
|
torch.cat(offset_parts, dim=0),
|
|
torch.cat(row_parts, dim=0),
|
|
torch.cat(time_parts, dim=0),
|
|
)
|
|
|
|
|
|
def reference_alignment(payload: dict[str, Any]) -> tuple[torch.Tensor, torch.Tensor]:
|
|
"""Require the same full, zero-origin 5 Hz timeline used by head training."""
|
|
states = payload.get("states")
|
|
if not isinstance(states, torch.Tensor) or states.ndim not in (2, 3) or not len(states):
|
|
raise ValueError("Reference must contain nonempty [T,D] or [T,L,D] states")
|
|
if float(payload.get("start", 0)) != 0:
|
|
raise ValueError("Local features require a zero-origin reference (start=0)")
|
|
indices = torch.as_tensor(payload.get("label_indices", []))
|
|
if indices.dtype != torch.long or not torch.equal(indices, torch.arange(len(states))):
|
|
raise ValueError("Reference label_indices must be dense int64 [0,...,T-1]")
|
|
times = torch.as_tensor(payload.get("times", []), dtype=torch.float64)
|
|
expected = (torch.arange(len(states), dtype=torch.float64) + 1) / 5
|
|
# Existing feature files may have serialized times as float32.
|
|
if times.shape != expected.shape or not torch.allclose(times, expected, atol=5e-4, rtol=0):
|
|
raise ValueError("Reference times must be [0.2,0.4,...] seconds at 5 Hz")
|
|
return times, indices
|
|
|
|
|
|
def _load_validated_payload(
|
|
path: Path,
|
|
reference: dict[str, Any],
|
|
*,
|
|
sample_id: str,
|
|
dataset: str,
|
|
modalities: str,
|
|
expected_contract: dict[str, Any] | None,
|
|
) -> tuple[torch.Tensor, torch.Tensor, dict[str, Any], dict[str, Any], dict[str, Any]]:
|
|
if modalities not in MODALITIES:
|
|
raise ValueError(f"Unknown local modalities: {modalities}")
|
|
times, indices = reference_alignment(reference)
|
|
payload = torch.load(path, map_location="cpu", weights_only=False)
|
|
if not isinstance(payload, dict) or payload.get("format") != LOCAL_FORMAT:
|
|
raise ValueError(f"Invalid local feature format: {path}")
|
|
if payload.get("sample_id") != sample_id or payload.get("dataset") != dataset:
|
|
raise ValueError(f"Local sample/dataset mismatch: {path}")
|
|
if payload.get("partial", False):
|
|
raise ValueError(f"Partial smoke-test features cannot be used for training: {path}")
|
|
local_indices = torch.as_tensor(payload.get("label_indices", []))
|
|
local_times = torch.as_tensor(payload.get("times", []), dtype=torch.float64)
|
|
if local_indices.dtype != torch.long or not torch.equal(indices, local_indices):
|
|
raise ValueError(f"Local label_indices mismatch: {path}")
|
|
if local_times.shape != times.shape or not torch.allclose(local_times, times, atol=1e-7, rtol=0):
|
|
raise ValueError(f"Local times mismatch: {path}")
|
|
config = payload.get("config", {})
|
|
if config.get("causal_policy") != "half-open-trailing-window" or config.get("uses_speech_labels") is not False:
|
|
raise ValueError(f"Local features lack the causal/no-speech-label contract: {path}")
|
|
contract = {"format": LOCAL_FORMAT, "modalities": modalities, "config": config}
|
|
if expected_contract is not None and contract != expected_contract:
|
|
raise ValueError(f"Local encoder/pooling contract differs across sessions/checkpoint: {path}")
|
|
return times, indices, payload, config, contract
|
|
|
|
|
|
def load_local_features(
|
|
path: Path,
|
|
reference: dict[str, Any],
|
|
*,
|
|
sample_id: str,
|
|
dataset: str,
|
|
modalities: str,
|
|
expected_contract: dict[str, Any] | None = None,
|
|
) -> tuple[torch.Tensor, dict[str, Any]]:
|
|
"""Pack each requested modality as [raw vector, validity bit]. Fail closed."""
|
|
times, _, payload, config, contract = _load_validated_payload(
|
|
path,
|
|
reference,
|
|
sample_id=sample_id,
|
|
dataset=dataset,
|
|
modalities=modalities,
|
|
expected_contract=expected_contract,
|
|
)
|
|
chunks = []
|
|
for name in MODALITIES[modalities]:
|
|
values = payload.get(name)
|
|
valid = payload.get(f"{name}_valid")
|
|
dimension = config.get(f"{name}_dim")
|
|
if not isinstance(dimension, int) or dimension <= 0:
|
|
raise ValueError(f"Missing {name}_dim: {path}")
|
|
if not isinstance(values, torch.Tensor) or values.shape != (len(times), dimension):
|
|
raise ValueError(f"Invalid {name} shape: {path}")
|
|
if not values.is_floating_point() or not torch.isfinite(values).all():
|
|
raise ValueError(f"Non-finite/non-floating {name} features: {path}")
|
|
if not isinstance(valid, torch.Tensor) or valid.dtype != torch.bool or valid.shape != (len(times),):
|
|
raise ValueError(f"Invalid {name}_valid mask: {path}")
|
|
if torch.count_nonzero(values[~valid]):
|
|
raise ValueError(f"Invalid {name} rows must be stored as zeros: {path}")
|
|
chunks.extend((values.float(), valid[:, None].float()))
|
|
return torch.cat(chunks, dim=-1), contract
|
|
|
|
|
|
def load_frame_set_features(
|
|
path: Path,
|
|
reference: dict[str, Any],
|
|
*,
|
|
sample_id: str,
|
|
dataset: str,
|
|
expected_contract: dict[str, Any] | None = None,
|
|
) -> tuple[torch.Tensor, FramePersonFeatures, dict[str, Any]]:
|
|
"""Load direct audio and the latest causal per-frame person set per 5 Hz row."""
|
|
|
|
times, _, payload, config, contract = _load_validated_payload(
|
|
path,
|
|
reference,
|
|
sample_id=sample_id,
|
|
dataset=dataset,
|
|
modalities="av",
|
|
expected_contract=expected_contract,
|
|
)
|
|
audio = payload.get("audio")
|
|
audio_valid = payload.get("audio_valid")
|
|
audio_dim = config.get("audio_dim")
|
|
if not isinstance(audio_dim, int) or audio_dim <= 0:
|
|
raise ValueError(f"Missing audio_dim: {path}")
|
|
if not isinstance(audio, torch.Tensor) or audio.shape != (len(times), audio_dim):
|
|
raise ValueError(f"Invalid audio shape: {path}")
|
|
if not audio.is_floating_point() or not torch.isfinite(audio).all():
|
|
raise ValueError(f"Non-finite/non-floating audio features: {path}")
|
|
if (
|
|
not isinstance(audio_valid, torch.Tensor)
|
|
or audio_valid.dtype != torch.bool
|
|
or audio_valid.shape != (len(times),)
|
|
):
|
|
raise ValueError(f"Invalid audio_valid mask: {path}")
|
|
if torch.count_nonzero(audio[~audio_valid]):
|
|
raise ValueError(f"Invalid audio rows must be stored as zeros: {path}")
|
|
|
|
visual_dim = config.get("visual_dim")
|
|
persons = payload.get("persons")
|
|
if not isinstance(visual_dim, int) or visual_dim <= 0:
|
|
raise ValueError(f"Missing visual_dim: {path}")
|
|
if not isinstance(persons, dict):
|
|
raise ValueError(f"Missing ragged person features: {path}")
|
|
features = persons.get("features")
|
|
frame_times = persons.get("frame_times")
|
|
frame_offsets = persons.get("frame_offsets")
|
|
records = persons.get("records")
|
|
if (
|
|
not isinstance(features, torch.Tensor)
|
|
or features.ndim != 2
|
|
or features.shape[1] != visual_dim
|
|
or not features.is_floating_point()
|
|
or not torch.isfinite(features).all()
|
|
):
|
|
raise ValueError(f"Invalid person feature shape/content: {path}")
|
|
if (
|
|
not isinstance(frame_times, torch.Tensor)
|
|
or frame_times.ndim != 1
|
|
or not frame_times.is_floating_point()
|
|
):
|
|
raise ValueError(f"Invalid person frame_times: {path}")
|
|
frame_times = frame_times.to(dtype=torch.float64)
|
|
if (
|
|
not torch.isfinite(frame_times).all()
|
|
or bool((frame_times < 0).any())
|
|
or bool((frame_times[1:] <= frame_times[:-1]).any())
|
|
):
|
|
raise ValueError(f"Person frame_times must be finite, nonnegative and increasing: {path}")
|
|
if (
|
|
not isinstance(frame_offsets, torch.Tensor)
|
|
or frame_offsets.dtype != torch.long
|
|
or frame_offsets.shape != (len(frame_times) + 1,)
|
|
or not len(frame_offsets)
|
|
or int(frame_offsets[0]) != 0
|
|
or int(frame_offsets[-1]) != len(features)
|
|
or bool((frame_offsets[1:] < frame_offsets[:-1]).any())
|
|
):
|
|
raise ValueError(f"Invalid person frame_offsets: {path}")
|
|
if not isinstance(records, list) or len(records) != len(features):
|
|
raise ValueError(f"Person records/features length mismatch: {path}")
|
|
if len(frame_times) and float(frame_times[-1]) > float(times[-1]) + 1e-8:
|
|
raise ValueError(f"Person frame timeline extends beyond the reference: {path}")
|
|
|
|
# Match the sidecar's half-open policy: a frame stamped exactly at the
|
|
# state cutoff is not yet part of that state's observed prefix.
|
|
row_to_frame = torch.searchsorted(frame_times, times, right=False) - 1
|
|
chosen = torch.full(times.shape, float("nan"), dtype=torch.float64)
|
|
has_frame = row_to_frame >= 0
|
|
chosen[has_frame] = frame_times[row_to_frame[has_frame]]
|
|
if bool((chosen[has_frame] >= times[has_frame]).any()):
|
|
raise ValueError(f"Person frame mapping selected future visual evidence: {path}")
|
|
frame_sets = FramePersonFeatures(
|
|
features,
|
|
frame_offsets,
|
|
row_to_frame.to(dtype=torch.long),
|
|
chosen,
|
|
)
|
|
direct_audio = torch.cat(
|
|
(audio.float(), audio_valid[:, None].float()),
|
|
dim=-1,
|
|
)
|
|
return direct_audio, frame_sets, contract
|
|
|
|
|
|
def local_head_dimensions(contract: dict[str, Any] | None) -> dict[str, int]:
|
|
if contract is None:
|
|
return {"local_visual_dim": 0, "local_audio_dim": 0}
|
|
selected = MODALITIES[contract["modalities"]]
|
|
return {
|
|
f"local_{name}_dim": int(contract["config"][f"{name}_dim"]) if name in selected else 0
|
|
for name in ("visual", "audio")
|
|
}
|
|
|
|
|
|
def causal_frame_ticks(end: float, fps: float) -> range:
|
|
"""Global fixed lattice [0,end), excluding the frame exactly at end."""
|
|
if end <= 0 or fps <= 0:
|
|
raise ValueError("end and fps must be positive")
|
|
return range(max(0, math.ceil(end * fps - 1e-8)))
|
|
|
|
|
|
def pooled_recent_visual(
|
|
frame_times: torch.Tensor,
|
|
frame_vectors: torch.Tensor,
|
|
frame_valid: torch.Tensor,
|
|
end: float,
|
|
window_seconds: float,
|
|
) -> tuple[torch.Tensor, bool]:
|
|
"""Equal frame weighting after equal person weighting within each frame."""
|
|
keep = ((frame_times >= max(0., end - window_seconds) - 1e-8)
|
|
& (frame_times < end - 1e-8) & frame_valid)
|
|
if not bool(keep.any()):
|
|
return frame_vectors.new_zeros(frame_vectors.shape[-1]), False
|
|
return frame_vectors[keep].float().mean(0), True
|
|
|
|
|
|
def easycom_boxes(rows: list[dict[str, Any]], kind: str) -> dict[int, list[dict[str, Any]]]:
|
|
"""Map EasyCom face (1-based) / head (0-based) records to decoded indices."""
|
|
if kind not in ("face", "head"):
|
|
raise ValueError(f"Unknown box kind: {kind}")
|
|
result = {}
|
|
for row in rows:
|
|
frame = int(row["Frame_Number"]) - (1 if kind == "face" else 0)
|
|
people = row.get("Participants", [])
|
|
if isinstance(people, dict):
|
|
people = [people]
|
|
if frame < 0 or frame in result or not isinstance(people, list):
|
|
raise ValueError("Invalid/duplicate EasyCom box frame")
|
|
result[frame] = [
|
|
{"id": str(p.get("Participant_ID", -1)),
|
|
"xyxy": [float(p[k]) for k in ("x1", "y1", "x2", "y2")]}
|
|
for p in people
|
|
]
|
|
return result
|
|
|
|
|
|
def crop_box(
|
|
xyxy: list[float], width: int, height: int, *,
|
|
offset_x: int = 0, offset_y: int = 0, expansion: float = 1.,
|
|
) -> tuple[int, int, int, int] | None:
|
|
"""Transform to camera coordinates, expand, clip; reject degenerate boxes."""
|
|
if len(xyxy) != 4 or not all(math.isfinite(v) for v in xyxy):
|
|
return None
|
|
x1, y1, x2, y2 = xyxy
|
|
if x2 <= x1 or y2 <= y1 or expansion <= 0:
|
|
return None
|
|
cx, cy = (x1 + x2) / 2 - offset_x, (y1 + y2) / 2 - offset_y
|
|
half_w, half_h = (x2 - x1) * expansion / 2, (y2 - y1) * expansion / 2
|
|
box = (max(0, math.floor(cx - half_w)), max(0, math.floor(cy - half_h)),
|
|
min(width, math.ceil(cx + half_w)), min(height, math.ceil(cy + half_h)))
|
|
w, h = box[2] - box[0], box[3] - box[1]
|
|
# Qwen's smart_resize rejects aspect ratios above 200 (e.g. a sliver of
|
|
# an offscreen box). Such a crop is not a usable person observation.
|
|
return box if min(w, h) >= 2 and max(w, h) / min(w, h) <= 200 else None
|