LayoutMatch/data_units.py

import numpy as np
from PIL import Image
import torchvision.transforms as transforms

def layout_transforms():
    """Define data augmentation and preprocessing."""
    return transforms.Compose([
        transforms.Resize((256, 256)),       # 调整尺寸到固定大小
        transforms.RandomRotation(30),       # 随机旋转（增强方向不变性）
        transforms.ColorJitter(brightness=0.2, contrast=0.2),  # 彩色抖动（如果使用图像数据）
        transforms.ToTensor(),               # 转换为张量
        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 标准化（如ImageNet均值和方差）
    ])

def layout_to_tensor(layout_path, target_size=(256, 256)):
    """Convert layout to normalized tensor."""
    img = Image.open(layout_path).convert('L')  # Convert to grayscale
    img = img.resize(target_size, resample=Image.BILINEAR)
    return np.array(img) / 255.0                # Normalize to [0,1]

def tile_layout(large_layout, block_size=64):
    """将大版图分割为小块（滑动窗口方式）"""
    height, width = large_layout.shape
    stride = block_size // 2                     # 步长设置重叠区域
    tiles = []
    for y in range(0, height - block_size +1, stride):
        for x in range(0, width - block_size +1, stride):
            tile = large_layout[y:y+block_size, x:x+block_size]
            tiles.append((x, y, tile))
    return tiles
    """将大版图分割为小块（滑动窗口方式）"""
def tile_layout(large_layout, block_size=64, overlap_ratio=0.5):
    """Split large layout into tiles with specified overlap."""
    height, width = large_layout.shape
    stride = block_size // 2                     # 步长设置重叠区域
    stride = int(block_size * (1 - overlap_ratio))  # Calculate step size based on overlap ratio
    tiles = []
    for y in range(0, height - block_size + 1, stride):
        for x in range(0, width - block_size + 1, stride):
            tile = large_layout[y:y+block_size, x:x+block_size]
            tiles.append((x, y, tile))
    return tiles