#!/usr/bin/env python3 """Upload Waymo-derived unified clips to a PRIVATE HF repo (owner's licensed-use backup; NOT redistribution). Waymo-only; AV2/code/checkpoints live in the public companion repo. Token from $HF_TOKEN.""" import os, glob, tarfile from huggingface_hub import HfApi, create_repo TOKEN = os.environ["HF_TOKEN"] REPO = os.environ.get("HF_REPO", "ChenmingWu/mapgs-waymo") ROOT = "/mnt/william" STAGE = "/mnt/william/_upload" SHARD_GB = 18.0 api = HfApi(token=TOKEN) def log(*a): print(*a, flush=True) def dir_size(d): s = 0 for r, _, fs in os.walk(d): for f in fs: try: s += os.path.getsize(os.path.join(r, f)) except OSError: pass return s def main(): create_repo(REPO, private=True, repo_type="model", exist_ok=True, token=TOKEN) log(f"PRIVATE repo ready: {REPO}") api.upload_file(path_or_fileobj=f"{ROOT}/README_WAYMO.md", path_in_repo="README.md", repo_id=REPO, repo_type="model") log("uploaded README") os.makedirs(STAGE, exist_ok=True) clip_dirs = sorted(d for d in glob.glob(f"{ROOT}/data/unified/waymo/*/*") if os.path.isdir(d)) assert clip_dirs and all("/av2/" not in d for d in clip_dirs), "non-Waymo path in shard set!" log(f"Waymo clip dirs: {len(clip_dirs)}") shards, cur, sz, cap = [], [], 0, SHARD_GB * 1e9 for d in clip_dirs: s = dir_size(d) if cur and sz + s > cap: shards.append(cur); cur, sz = [], 0 cur.append(d); sz += s if cur: shards.append(cur) log(f"{len(shards)} Waymo shards") for i, dirs in enumerate(shards): tarp = f"{STAGE}/waymo_shard_{i:03d}.tar" with tarfile.open(tarp, "w") as tf: for d in dirs: tf.add(d, arcname=os.path.relpath(d, ROOT)) gb = os.path.getsize(tarp) / 1e9 api.upload_file(path_or_fileobj=tarp, path_in_repo=f"data/waymo_shard_{i:03d}.tar", repo_id=REPO, repo_type="model") os.remove(tarp) log(f"uploaded waymo_shard_{i:03d}.tar ({gb:.1f} GB, {len(dirs)} clips) [{i+1}/{len(shards)}]") log("=== WAYMO PRIVATE UPLOAD COMPLETE ===") if __name__ == "__main__": main()