Spaces:
Sleeping
Sleeping
Download blockdiffusion/data/texture_folder.py from wkea/blockdiffusion-api: direct link, hf CLI and curl.
- Browser
- Download file 2.23 kB
-
https://huggingface.co/spaces/wkea/blockdiffusion-api/resolve/main/blockdiffusion/data/texture_folder.py
- Command line
-
hf download hf://spaces/wkea/blockdiffusion-api/blockdiffusion/data/texture_folder.py
-
curl -L -o texture_folder.py https://huggingface.co/spaces/wkea/blockdiffusion-api/resolve/main/blockdiffusion/data/texture_folder.py
2.23 kB
| from __future__ import annotations | |
| import os | |
| from typing import List, Sequence, Tuple | |
| from PIL import Image | |
| import torch | |
| from torch.utils.data import Dataset | |
| from torchvision import transforms as T | |
| _IMG_EXTS = (".png", ".jpg", ".jpeg", ".webp", ".bmp") | |
| def _list_images(root: str) -> List[str]: | |
| paths: List[str] = [] | |
| for dirpath, _, filenames in os.walk(root): | |
| for fn in filenames: | |
| if fn.lower().endswith(_IMG_EXTS): | |
| paths.append(os.path.join(dirpath, fn)) | |
| paths.sort() | |
| return paths | |
| class TextureFolderDataset(Dataset): | |
| """ | |
| 纹理图片数据集: | |
| - 读取目录下所有图片(含子目录) | |
| - 统一转换为 RGB | |
| - 缩放到 16×16 | |
| - 输出范围为 [-1, 1] 的张量(C,H,W) | |
| """ | |
| def __init__( | |
| self, | |
| root_dir: str, | |
| image_size: int = 16, | |
| channels: int = 3, | |
| random_flip: bool = True, | |
| ): | |
| self.root_dir = root_dir | |
| self.image_size = int(image_size) | |
| self.channels = int(channels) | |
| if self.channels not in (3, 4): | |
| raise ValueError("channels 仅支持 3(RGB) 或 4(RGBA)") | |
| self.paths = _list_images(root_dir) | |
| if len(self.paths) == 0: | |
| raise ValueError(f"数据集目录为空或未找到图片:{root_dir}") | |
| tfms = [ | |
| T.Resize((self.image_size, self.image_size), interpolation=T.InterpolationMode.NEAREST), | |
| ] | |
| if random_flip: | |
| tfms.append(T.RandomHorizontalFlip(p=0.5)) | |
| tfms.extend( | |
| [ | |
| T.ToTensor(), # [0,1] | |
| # 用 Normalize 替代 lambda,保证 Windows 多进程 DataLoader 可 pickle | |
| T.Normalize(mean=[0.5] * self.channels, std=[0.5] * self.channels), # [-1,1] | |
| ] | |
| ) | |
| self.transform = T.Compose(tfms) | |
| def __len__(self) -> int: | |
| return len(self.paths) | |
| def __getitem__(self, idx: int) -> torch.Tensor: | |
| path = self.paths[idx] | |
| # 使用 nearest resize,尽量保留像素风格边缘 | |
| with Image.open(path) as im: | |
| im = im.convert("RGBA" if self.channels == 4 else "RGB") | |
| x = self.transform(im) | |
| return x | |