42 lines
2.0 KiB
Python
42 lines
2.0 KiB
Python
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 |