| from __future__ import annotations |
|
|
| import argparse |
| import json |
| import math |
| import os |
|
|
| import numpy as np |
| import torch |
| from PIL import Image |
|
|
| from dit import DiT |
|
|
| Image.MAX_IMAGE_PIXELS = None |
|
|
| def build(cfg): |
| return DiT(dim=cfg["dim"], depth=cfg["depth"], heads=cfg["heads"]) |
|
|
| def encode(ckpt, png_path, cfg_path, dim=384, depth=12, heads=6, which="ema"): |
| ck = torch.load(ckpt, map_location="cpu") |
| cfg = {"dim": dim, "depth": depth, "heads": heads} |
| model = build(cfg) |
| 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) |
| json.dump({"cfg": cfg, "params": manifest, "total_parameters": int(N), |
| "side": side, "dtype": "float16", "channels": "R=hi,G=lo,B=unused", |
| "step": ck.get("step"), "val_loss": ck.get("val")}, |
| open(cfg_path, "w")) |
| print(f"[png] encoded {N:,} params into a {side}x{side} PNG " |
| f"({os.path.getsize(png_path)/1e6:.1f} MB)") |
| return N, side |
|
|
| def load_model_png(png_path, cfg_path, device="cpu"): |
| meta = json.load(open(cfg_path)) |
| model = build(meta["cfg"]) |
| 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) |
| sd[m["name"]].copy_(torch.from_numpy(chunk.copy()).view(*m["shape"]).to(torch.float32)) |
| off += n |
| return model.to(device).eval() |
|
|
| def verify(ckpt, png_path, cfg_path, which="ema"): |
| model = load_model_png(png_path, cfg_path) |
| ref = torch.load(ckpt, map_location="cpu")[which] |
| worst, name = 0.0, "" |
| for k, p in model.named_parameters(): |
| d = (p.detach() - ref[k].float()).abs().max().item() |
| if d > worst: |
| worst, name = d, k |
| scale = max(1e-12, ref[name].float().abs().max().item()) |
| print(f"[png] round-trip max abs error {worst:.3e} on {name} (relative {worst/scale:.2e})") |
| return worst |
|
|
| def main(): |
| ap = argparse.ArgumentParser() |
| ap.add_argument("--ckpt", default="/root/runs/pm5/best.pt") |
| ap.add_argument("--png", default="model.png") |
| ap.add_argument("--manifest", default="model_png.json") |
| args = ap.parse_args() |
| encode(args.ckpt, args.png, args.manifest) |
| verify(args.ckpt, args.png, args.manifest) |
|
|
| if __name__ == "__main__": |
| main() |
|
|
