png_codec.py

from __future__ import annotations
import argparse, json, math
import numpy as np
import torch
from PIL import Image
from dit import DiT

def encode(ckpt, png_path, cfg_path, which="ema"):
    ck = torch.load(ckpt, map_location="cpu")
    c = ck["cfg"]
    model = DiT(dim=c["dim"], depth=c["depth"], heads=c["heads"])
    model.load_state_dict(ck[which])
    parts, manifest = [], []
    for name, p in model.named_parameters():
        a = p.detach().to(torch.float16).contiguous().view(-1).numpy()
        parts.append(a)
        manifest.append({"name": name, "shape": list(p.shape), "numel": int(a.size)})
    flat = np.concatenate(parts)
    N = flat.size
    side = math.ceil(math.sqrt(N))
    u16 = flat.view(np.uint16)
    img = np.zeros((side * side, 3), dtype=np.uint8)
    img[:N, 0] = (u16 >> 8).astype(np.uint8)
    img[:N, 1] = (u16 & 0xFF).astype(np.uint8)
    Image.fromarray(img.reshape(side, side, 3), "RGB").save(png_path)
    total = sum(m["numel"] for m in manifest)
    with open(cfg_path, "w") as f:
        json.dump({"cfg": c, "params": manifest, "total_parameters": total,
                   "side": side, "dtype": "float16", "channels": "R=hi,G=lo,B=unused"}, f)
    import os
    mb = os.path.getsize(png_path) / 1e6
    print(f"[png] encoded {total:,} params -> {side}x{side} PNG ({mb:.1f} MB)", flush=True)
    return total, side

def load_model_png(png_path, cfg_path, device="cpu"):
    meta = json.load(open(cfg_path))
    c = meta["cfg"]
    model = DiT(dim=c["dim"], depth=c["depth"], heads=c["heads"])
    arr = np.asarray(Image.open(png_path).convert("RGB")).reshape(-1, 3)
    total = meta["total_parameters"]
    hi = arr[:total, 0].astype(np.uint16)
    lo = arr[:total, 1].astype(np.uint16)
    flat = ((hi << 8) | lo).astype(np.uint16).view(np.float16)
    sd = dict(model.named_parameters())
    off = 0
    with torch.no_grad():
        for m in meta["params"]:
            n = m["numel"]
            chunk = flat[off:off + n].astype(np.float16)
            t = torch.from_numpy(chunk.copy()).view(*m["shape"]).to(torch.float32)
            sd[m["name"]].copy_(t)
            off += n
    return model.to(device).eval()

def decode_and_verify(png_path, cfg_path, ckpt=None, which="ema"):
    model = load_model_png(png_path, cfg_path)
    print(f"[png] decoded -> DiT with {sum(p.numel() for p in model.parameters()):,} params", flush=True)
    if ckpt:
        ck = torch.load(ckpt, map_location="cpu")
        ref = DiT(dim=ck["cfg"]["dim"], depth=ck["cfg"]["depth"], heads=ck["cfg"]["heads"])
        ref.load_state_dict(ck[which])
        maxdiff = 0.0
        for (n1, p1), (n2, p2) in zip(model.named_parameters(), ref.named_parameters()):
            maxdiff = max(maxdiff, (p1.float() - p2.half().float()).abs().max().item())
        print(f"[png] max |decoded - original(fp16)| = {maxdiff:.2e}  (0 == lossless)", flush=True)
    return model

if __name__ == "__main__":
    ap = argparse.ArgumentParser()
    ap.add_argument("mode", choices=["encode", "decode"])
    ap.add_argument("--ckpt", default="ckpt/final.pt")
    ap.add_argument("--png", default="model.png")
    ap.add_argument("--config", default="model_png.json")
    ap.add_argument("--which", default="ema")
    args = ap.parse_args()
    if args.mode == "encode":
        encode(args.ckpt, args.png, args.config, args.which)
    else:
        decode_and_verify(args.png, args.config, args.ckpt, args.which)