| from __future__ import annotations |
|
|
| import argparse |
| import json |
| import math |
| import os |
|
|
| import numpy as np |
| import torch |
| from PIL import Image |
| from safetensors.torch import load_file |
|
|
| from voxel_dit import VoxelDiT |
|
|
| def encode(weights, png_path, cfg_path, config="config.json"): |
| c = json.load(open(config))["dit"] |
| model = VoxelDiT(vox_size=c["vox_size"], patch=c["patch"], dim=c["dim"], |
| depth=c["depth"], heads=c["heads"], text_dim=c["text_dim"]) |
| model.load_state_dict(load_file(weights)) |
| 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) |
| json.dump({"cfg": c, "params": manifest, "total_parameters": total, |
| "side": side, "dtype": "float16", "channels": "R=hi,G=lo,B=unused"}, |
| open(cfg_path, "w")) |
| mb = os.path.getsize(png_path) / 1e6 |
| print(f"[png] encoded {total:,} params -> {side}x{side} PNG ({mb:.1f} MB)") |
| return total, side |
|
|
| def load_model_png(png_path, cfg_path, device="cpu"): |
| meta = json.load(open(cfg_path)) |
| c = meta["cfg"] |
| model = VoxelDiT(vox_size=c["vox_size"], patch=c["patch"], dim=c["dim"], |
| depth=c["depth"], heads=c["heads"], text_dim=c["text_dim"]) |
| 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(weights, png_path, cfg_path, config="config.json"): |
| model = load_model_png(png_path, cfg_path) |
| ref = load_file(weights) |
| 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 |
| rel = worst / max(1e-12, ref[name].float().abs().max().item()) |
| print(f"[png] round-trip max abs err {worst:.3e} on {name} (relative {rel:.2e})") |
| return worst |
|
|
| def main(): |
| ap = argparse.ArgumentParser() |
| ap.add_argument("--weights", default="model.safetensors") |
| ap.add_argument("--png", default="model.png") |
| ap.add_argument("--manifest", default="model_png.json") |
| ap.add_argument("--config", default="config.json") |
| args = ap.parse_args() |
| encode(args.weights, args.png, args.manifest, args.config) |
| verify(args.weights, args.png, args.manifest, args.config) |
|
|
| if __name__ == "__main__": |
| main() |
|
|
