Download scale/script/prepare_simple_text.py from Tinghong-Ye22/code-Movens-Zero_train: direct link, hf CLI and curl.
- Browser
- Download file 4.4 kB
-
https://huggingface.co/Tinghong-Ye22/code-Movens-Zero_train/resolve/main/scale/script/prepare_simple_text.py
- Command line
-
hf download hf://Tinghong-Ye22/code-Movens-Zero_train/scale/script/prepare_simple_text.py
-
curl -L -o prepare_simple_text.py https://huggingface.co/Tinghong-Ye22/code-Movens-Zero_train/resolve/main/scale/script/prepare_simple_text.py
4.4 kB
| """Prepare short, exactly training-caption-matched inputs for the original v4 protocol.""" | |
| import argparse | |
| import csv | |
| import hashlib | |
| import json | |
| from pathlib import Path | |
| import sys | |
| ROOT = Path(__file__).resolve().parents[2] | |
| CASES = ( | |
| ('simple_walk_forward', 't0000103', 'g00', '直行(训练原文)'), | |
| ('simple_walk_circle', 't0003078', 'g02', '逆时针行走(训练原文)'), | |
| ('simple_squats', 't0003075', 'g02', '三次深蹲(训练原文)'), | |
| ) | |
| def prepare(run, output): | |
| import numpy as np | |
| runtime = json.loads((ROOT / 'config/runtime.json').read_text()) | |
| code = Path(runtime['visualization_resources']).parent | |
| sys.path.insert(0, str(code / 'OmniHM_bench')) | |
| from video_motion import load_motion36, sample_motion36, motion36_to_qpos, G1_MUJOCO_JOINT_NAMES | |
| from preview_scale import save | |
| manifest_path = output / 'manifest.json' | |
| if manifest_path.exists(): | |
| m = json.loads(manifest_path.read_text()) | |
| if m['source_run'] != str(run) or [c['id'] for c in m['cases']] != [c[0] for c in CASES]: | |
| raise ValueError('Existing simple-text selection does not match this run') | |
| return | |
| manifest = dict(source_run=str(run), selection_only=True, checkpoint_step=None, | |
| representation='root40_v1', normalization='g1_root40_fixed_v1', inference_fps=50, | |
| denoising_steps=10, action_chunk=30, execution_horizon=20, selection_seed=20261002, | |
| protocol='GT frame 0 initialization; free autoregressive rollout; no future GT poses', | |
| selection_version='simple_training_text_v1', cases=[]) | |
| hashes = {} | |
| for index, (identity, motion_id, group, label) in enumerate(CASES): | |
| source_manifest = ROOT / f'training_set/text/index/{group}.csv' | |
| row = next(r for r in csv.DictReader(source_manifest.open()) if r['move_name'] == motion_id) | |
| source = ROOT / 'training_set/text' / row['move_g1_path'] | |
| motion = load_motion36(source) | |
| # Keep the entire training sequence and the original gallery's 30 Hz display. | |
| times = np.arange(int(np.floor((len(motion)-1)*30/50))+1) / 30 | |
| qpos = motion36_to_qpos(sample_motion36(motion, source_fps=50, sample_times=times)).astype(np.float32) | |
| directory = output / 'text' / identity | |
| directory.mkdir(parents=True, exist_ok=True) | |
| record = dict(sample_id=identity, caption=row['content_short_description'], source_motion_path=str(source), | |
| training_id=f'text_{group} / {motion_id}', source_manifest=str(source_manifest), | |
| data_split='训练集内固定样例(不是独立验证集)', label=label, | |
| source_sha256={n:hashlib.sha256((source/n).read_bytes()).hexdigest() | |
| for n in ('joint_pos.csv','body_pos.csv','body_quat.csv')}) | |
| save(directory / 'selection_record.json', record) | |
| np.savez_compressed(directory / 'gt.npz', qpos_36=qpos, valid=np.ones(len(qpos),bool), fps=30., | |
| joint_names=np.asarray(G1_MUJOCO_JOINT_NAMES), sample_id=identity, score_start_frame=1) | |
| case = dict(id=identity, modality='text', directory=f'text/{identity}', caption=row['content_short_description'], | |
| seed=20261002+index, fps=30., frames=len(qpos), source_sequence=motion_id, input_media=None, | |
| status='selected', label=label) | |
| manifest['cases'].append(case) | |
| for name in ('selection_record.json','gt.npz'): | |
| hashes[f'text/{identity}/{name}'] = hashlib.sha256((directory/name).read_bytes()).hexdigest() | |
| contract = [{k:c[k] for k in ('id','directory','seed','fps','frames','source_sequence')} for c in manifest['cases']] | |
| manifest['fixed_input_sha256'] = hashes | |
| manifest['fixed_case_contract_sha256'] = hashlib.sha256(json.dumps(contract,sort_keys=True,separators=(',',':')).encode()).hexdigest() | |
| save(manifest_path, manifest) | |
| if __name__ == '__main__': | |
| parser = argparse.ArgumentParser(description=__doc__) | |
| parser.add_argument('--run', type=Path, required=True) | |
| parser.add_argument('--output', type=Path, required=True) | |
| args = parser.parse_args() | |
| run, output = args.run.resolve(strict=True), args.output.resolve() | |
| if not run.is_relative_to(ROOT/'scale/groups') or not output.is_relative_to(ROOT/'scale/groups'): | |
| parser.error('Only scale experiment inputs may be prepared') | |
| prepare(run, output) | |