Download scripts/save_motion_teacher_hidden_cache.py from Tinghong-Ye22/code-Psi0-yth-v25: direct link, hf CLI and curl.
- Browser
- Download file 4.95 kB
-
https://huggingface.co/Tinghong-Ye22/code-Psi0-yth-v25/resolve/main/scripts/save_motion_teacher_hidden_cache.py
- Command line
-
hf download hf://Tinghong-Ye22/code-Psi0-yth-v25/scripts/save_motion_teacher_hidden_cache.py
-
curl -L -o save_motion_teacher_hidden_cache.py https://huggingface.co/Tinghong-Ye22/code-Psi0-yth-v25/resolve/main/scripts/save_motion_teacher_hidden_cache.py
4.95 kB
| from __future__ import annotations | |
| from dotenv import load_dotenv | |
| assert load_dotenv(), "Failed to load .env file. Make sure it exists and is properly formatted." | |
| import importlib | |
| import os | |
| import sys | |
| from pathlib import Path | |
| from typing import Any | |
| import torch | |
| import tyro | |
| from tqdm import tqdm | |
| from psi.data.dataset import MixtureDataset | |
| from psi.trainers import Trainer | |
| from psi.trainers.qwen2_5omni_mixin import PaddedCollatorForTogether | |
| from psi.utils import batch_str_to_tensor, initialize_overwatch, move_to_device, seed_everything | |
| overwatch = initialize_overwatch(__name__) | |
| def _dataset_items(dataset: Any, name: str): | |
| if isinstance(dataset, MixtureDataset): | |
| for idx, sub_dataset in enumerate(dataset.datasets): | |
| yield from _dataset_items(sub_dataset, f"{name}_mix{idx}") | |
| return | |
| if isinstance(dataset, dict): | |
| for key, sub_dataset in dataset.items(): | |
| yield from _dataset_items(sub_dataset, f"{name}_{key}") | |
| return | |
| yield name, dataset | |
| def _save_batch(trainer, collator, instances, split_name: str, save_dtype: torch.dtype) -> int: | |
| batch = batch_str_to_tensor(collator(instances)) | |
| batch = move_to_device(batch, trainer.device) | |
| with torch.no_grad(): | |
| hidden = trainer.model.encode_motion_hidden(batch["actions"]) | |
| saved = 0 | |
| for i in range(int(batch["input_ids"].shape[0])): | |
| cache_path, latent_hash = trainer._latent_cache_key(batch, i) | |
| cache_path.parent.mkdir(parents=True, exist_ok=True) | |
| obj = { | |
| "hidden_states": hidden[i].detach().to(dtype=save_dtype).cpu(), | |
| "latent_hash": latent_hash, | |
| "split": split_name, | |
| "task_name": trainer._batch_item(batch, "task_name", i, default="unknown"), | |
| "motion_dir": trainer._batch_item(batch, "motion_dir", i, default=""), | |
| "video_path": trainer._batch_item(batch, "video_path", i, default=""), | |
| "frame_id": str(trainer._batch_item(batch, "frame_id", i, default="")), | |
| } | |
| torch.save(obj, cache_path) | |
| saved += 1 | |
| return saved | |
| def save_cache(config): | |
| if config.seed: | |
| seed_everything(config.seed) | |
| cache_dir = getattr(config.model, "motion_latent_cache_dir", None) | |
| if not cache_dir: | |
| raise ValueError("--model.motion-latent-cache-dir must be set") | |
| teacher_checkpoint = getattr(config.model, "motion_teacher_checkpoint", None) | |
| if not teacher_checkpoint: | |
| raise ValueError("--model.motion-teacher-checkpoint must point to the stage-1 checkpoint") | |
| if torch.cuda.is_available(): | |
| torch.cuda.set_device(0) | |
| device = torch.device("cuda:0") | |
| else: | |
| device = torch.device("cpu") | |
| trainer = Trainer.instantiate(config, device) | |
| trainer.init_models() | |
| trainer.model.motion_encoder.to(device) | |
| trainer.model.motion_encoder.eval() | |
| train_dataset, val_dataset = trainer.create_datasets() | |
| datasets = [("train", train_dataset)] | |
| if val_dataset is not None: | |
| datasets.append(("val", val_dataset)) | |
| collator = PaddedCollatorForTogether( | |
| model_max_length=trainer.tokenizer.model_max_length, | |
| pad_token_id=trainer.tokenizer.pad_token_id, | |
| padding_side="right", | |
| ) | |
| batch_size = max(1, int(config.train.val_batch_size)) | |
| save_dtype = torch.bfloat16 if config.train.mixed_precision == "bf16" else torch.float32 | |
| total_saved = 0 | |
| for split_name, split_dataset in datasets: | |
| for dataset_name, dataset in _dataset_items(split_dataset, split_name): | |
| pending = [] | |
| progress = tqdm( | |
| range(len(dataset)), | |
| desc=f"Cache {dataset_name}", | |
| disable=not overwatch.is_rank_zero(), | |
| ) | |
| for idx in progress: | |
| pending.append(dataset[idx]) | |
| if len(pending) >= batch_size: | |
| total_saved += _save_batch(trainer, collator, pending, split_name, save_dtype) | |
| pending = [] | |
| progress.set_postfix(saved=total_saved) | |
| if pending: | |
| total_saved += _save_batch(trainer, collator, pending, split_name, save_dtype) | |
| cache_root = Path(str(cache_dir)) | |
| manifest_path = cache_root / "manifest.txt" | |
| if overwatch.is_rank_zero(): | |
| manifest_path.parent.mkdir(parents=True, exist_ok=True) | |
| with manifest_path.open("w") as f: | |
| f.write(f"teacher_checkpoint={teacher_checkpoint}\n") | |
| f.write(f"saved={total_saved}\n") | |
| overwatch.info(f"Saved {total_saved} motion latent cache entries to {cache_root}") | |
| def main(): | |
| module = importlib.import_module(f"psi.config.train.{sys.argv[1]}") | |
| config_cls = getattr(module, "DynamicLaunchConfig") | |
| config = tyro.cli( | |
| config_cls, | |
| config=(tyro.conf.ConsolidateSubcommandArgs,), | |
| args=sys.argv[2:], | |
| ) | |
| save_cache(config) | |
| if __name__ == "__main__": | |
| main() | |