wx44wx/icassp2027-experiment
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add EasyCom encoder-only comparison workflow

Browse Source
This commit is contained in:
Xin Wang
2026-08-28 10:44:13 +08:00
parent ee5e735fc2
commit 321238a92f
8 changed files with 488 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
run_ego4d_encoder_only.py
View File

@@ -1,7 +1,8 @@
"""Run raw encoder-only Ego4D heads: four epochs, no dev, manifest splits.
"""Run raw encoder-only heads: four epochs, no dev, fixed benchmark splits.
This is not a capacity/context-matched Thinker ablation: native encoder vectors
and validity flags are concatenated, so the existing MLP adapts to input width.
This entry defaults to Ego4D; run_easycom_encoder_only.py shares the workflow.
"""
from __future__ import annotations
@@ -15,32 +16,44 @@ import sys
from tqdm.auto import tqdm
from easycom_head import load_ego4d_manifest_split, load_session_data
from easycom_head import DATASET_NAMES, load_session_data
from local_turn_features import LOCAL_FORMAT, MODALITIES
from prepare_encoder_only_features import DEFAULT_DATA_ROOT, PACKING, encoder_only_mode
from prepare_encoder_only_features import (
DEFAULT_DATA_ROOTS, PACKING, encoder_only_mode, encoder_sample_split, sample_unit,
)
REPO = Path(__file__).resolve().parent
def parse_args(argv=None):
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--data-root", type=Path, default=DEFAULT_DATA_ROOT)
def parse_args(argv=None, *, dataset="ego4d"):
if dataset not in DATASET_NAMES:
raise ValueError(f"Unknown dataset: {dataset}")
parser = argparse.ArgumentParser(
description=f"{dataset}: raw encoder-only A/V/AV heads; four epochs, no dev, fixed train/test splits."
)
parser.add_argument("--data-root", type=Path, default=DEFAULT_DATA_ROOTS[dataset])
parser.add_argument("--manifest", type=Path)
parser.add_argument("--target-root", type=Path)
parser.add_argument("--feature-root", type=Path, required=True, help="Prepared encoder-only inputs, not Thinker/local sidecars")
parser.add_argument("--modalities", choices=tuple(MODALITIES), default="av")
parser.add_argument("--checkpoint-root", type=Path, default=Path("checkpoints/ego4d_encoder_only_1s"))
parser.add_argument("--result-root", type=Path, default=Path("results/ego4d_encoder_only_1s"))
parser.add_argument("--checkpoint-root", type=Path, default=Path(f"checkpoints/{dataset}_encoder_only_1s"))
parser.add_argument("--result-root", type=Path, default=Path(f"results/{dataset}_encoder_only_1s"))
parser.add_argument("--seeds", type=int, nargs="+", default=[0, 1, 2])
parser.add_argument("--device", default="cuda:0")
parser.add_argument("--dry-run", action="store_true", help="Validate all train/test inputs and print commands without training")
parser.add_argument("--no-progress", action="store_true")
args = parser.parse_args(argv)
args.manifest = args.manifest or args.data_root / "ego4d_egospeak.tsv"
args.target_root = args.target_root or args.data_root / "ego4d_target_frame"
args.dataset = dataset
if dataset == "ego4d":
args.manifest = args.manifest or args.data_root / "ego4d_egospeak.tsv"
elif args.manifest is not None:
parser.error("EasyCom uses train sessions 4..12 and test sessions 3/2/1, not --manifest")
args.target_root = args.target_root or args.data_root / f"{dataset}_target_frame"
for key in ("data_root", "manifest", "target_root", "feature_root", "checkpoint_root", "result_root"):
setattr(args, key, getattr(args, key).expanduser().resolve())
value = getattr(args, key)
if value is not None:
setattr(args, key, value.expanduser().resolve())
if len(set(args.seeds)) != len(args.seeds) or any(seed < 0 for seed in args.seeds):
parser.error("Seeds must be unique and nonnegative")
return args
@@ -52,19 +65,18 @@ def run_paths(args, seed):
def preflight(args):
names = load_ego4d_manifest_split(args.manifest, "all")
train = load_ego4d_manifest_split(args.manifest, "train")
test = load_ego4d_manifest_split(args.manifest, "test")
names, train, test = encoder_sample_split(args.dataset, args.manifest)
unit = sample_unit(args.dataset)
marker = args.feature_root / "complete.txt"
if not marker.is_file() or marker.read_text().strip() != f"{len(names)} clips":
if not marker.is_file() or marker.read_text().strip() != f"{len(names)} {unit}s":
raise ValueError(f"Missing/incomplete encoder-only export: {marker}")
for seed in args.seeds:
checkpoint, result = run_paths(args, seed)
if checkpoint.exists() or checkpoint.with_suffix(".pth.json").exists() or result.exists():
raise FileExistsError(f"Refusing to overwrite {checkpoint} or {result}; choose unfinished seeds/new output roots")
expected, total, width = None, 0, None
for name in tqdm(names, desc="encoder-only inputs", unit="clip", disable=args.no_progress):
data = load_session_data(args.feature_root, args.target_root, name, dataset="ego4d",
for name in tqdm(names, desc="encoder-only inputs", unit=unit, disable=args.no_progress):
data = load_session_data(args.feature_root, args.target_root, name, dataset=args.dataset,
expected_mode=encoder_only_mode(args.modalities))
config = data.feature_metadata.get("config") or {}
contract = config.get("encoder_contract") or {}
@@ -83,20 +95,21 @@ def preflight(args):
if data.states.ndim != 2 or data.hidden_size != width or len(data.states) <= 10:
raise ValueError(f"{name}: invalid native encoder-vector/validity-bit shape")
if expected is not None and config != expected:
raise ValueError(f"{name}: encoder export contract differs across clips")
raise ValueError(f"{name}: encoder export contract differs across {unit}s")
expected = config
total += len(data.states)
del data
print(f"Encoder-only {args.modalities}: {len(train)} train / {len(test)} test; "
print(f"{args.dataset} encoder-only {args.modalities}: {len(train)} train / {len(test)} test; "
f"{total} states, input width={width}, MLP hidden width={width // 2}; epochs=4, dev=none", flush=True)
print("No Thinker features or local-fusion branch. Native concatenation changes head capacity; "
"context remains the saved encoder windows.", flush=True)
def experiment_commands(args):
common = ["--dataset", "ego4d", "--manifest", str(args.manifest),
"--feature-root", str(args.feature_root), "--target-root", str(args.target_root),
common = ["--dataset", args.dataset, "--feature-root", str(args.feature_root), "--target-root", str(args.target_root),
"--expected-mode", encoder_only_mode(args.modalities), "--device", args.device]
if args.manifest is not None:
common += ["--manifest", str(args.manifest)]
if args.no_progress:
common.append("--no-progress")
for seed in args.seeds:
@@ -108,11 +121,15 @@ def experiment_commands(args):
"--transition-objective", "none", "--seed", str(seed)]
infer = [sys.executable, str(REPO / "infer_turn_head.py"), *common,
"--checkpoint", str(checkpoint), "--output-dir", str(result)]
if args.dataset == "easycom":
_, train_sessions, test_sessions = encoder_sample_split("easycom")
train += ["--sessions", *train_sessions]
infer += ["--sessions", *test_sessions]
yield train, infer
def main(argv=None):
args = parse_args(argv)
def main(argv=None, *, dataset="ego4d"):
args = parse_args(argv, dataset=dataset)
preflight(args)
env = os.environ.copy()
for name in ("OMP_NUM_THREADS", "MKL_NUM_THREADS", "OPENBLAS_NUM_THREADS"):
@@ -123,7 +140,7 @@ def main(argv=None):
if not args.dry_run:
subprocess.run(command, cwd=REPO, env=env, check=True)
summary = [sys.executable, str(REPO / "summarize_local_baselines.py"),
"--root", str(args.result_root), "--dataset", "ego4d"]
"--root", str(args.result_root), "--dataset", args.dataset]
print(shlex.join(summary), flush=True)
if not args.dry_run:
subprocess.run(summary, cwd=REPO, env=env, check=True)