dataset.py (6158B)
1 import os 2 from PIL import Image 3 import numpy as np 4 import cv2 5 6 import torch 7 from torch.utils.data import Dataset, DataLoader, WeightedRandomSampler 8 from torchvision import transforms 9 from sklearn.model_selection import train_test_split 10 11 IMAGENET_MEAN = [0.485, 0.456, 0.406] 12 IMAGENET_STD = [0.229, 0.224, 0.225] 13 14 15 class CLAHETransform: 16 """Apply CLAHE to the L channel of LAB color space. 17 18 Operates on PIL Images; returns a PIL Image. 19 """ 20 21 def __init__(self, clip_limit: float = 2.0, tile_grid_size: tuple = (8, 8)): 22 self.clahe = cv2.createCLAHE(clipLimit=clip_limit, tileGridSize=tile_grid_size) 23 24 def __call__(self, img: Image.Image) -> Image.Image: 25 img_np = np.array(img) # RGB uint8 26 lab = cv2.cvtColor(img_np, cv2.COLOR_RGB2LAB) 27 lab[:, :, 0] = self.clahe.apply(lab[:, :, 0]) 28 result = cv2.cvtColor(lab, cv2.COLOR_LAB2RGB) 29 return Image.fromarray(result) 30 31 32 class DRDataset(Dataset): 33 """Diabetic Retinopathy dataset from flat class-folder layout.""" 34 35 def __init__(self, image_paths: list, labels: list, transform=None): 36 self.image_paths = image_paths 37 self.labels = labels 38 self.transform = transform 39 40 def __len__(self) -> int: 41 return len(self.image_paths) 42 43 def __getitem__(self, idx: int): 44 img = Image.open(self.image_paths[idx]).convert('RGB') 45 label = self.labels[idx] 46 if self.transform is not None: 47 img = self.transform(img) 48 return img, label 49 50 51 def split_dataset(data_root: str, seed: int = 42): 52 """Scan class folders 0–4 and return stratified 70/15/15 splits. 53 54 Returns: 55 (train_paths, train_labels, val_paths, val_labels, test_paths, test_labels) 56 """ 57 all_paths, all_labels = [], [] 58 for class_idx in range(5): 59 class_dir = os.path.join(data_root, str(class_idx)) 60 for fname in sorted(os.listdir(class_dir)): 61 if fname.lower().endswith(('.jpg', '.jpeg', '.png')): 62 all_paths.append(os.path.join(class_dir, fname)) 63 all_labels.append(class_idx) 64 65 # 70% train, 30% temp 66 train_paths, temp_paths, train_labels, temp_labels = train_test_split( 67 all_paths, all_labels, test_size=0.30, stratify=all_labels, random_state=seed 68 ) 69 # 50/50 of temp -> 15% val, 15% test 70 val_paths, test_paths, val_labels, test_labels = train_test_split( 71 temp_paths, temp_labels, test_size=0.50, stratify=temp_labels, random_state=seed 72 ) 73 74 print(f"Dataset split — train: {len(train_paths)}, val: {len(val_paths)}, test: {len(test_paths)}") 75 return train_paths, train_labels, val_paths, val_labels, test_paths, test_labels 76 77 78 def build_transforms(use_clahe: bool, training: bool, img_size: int = 224): 79 """Build a transform pipeline for training or eval. 80 81 Training path uses RandomResizedCrop for scale/position augmentation. 82 Eval path uses a deterministic Resize to preserve comparability. 83 CLAHE is applied before spatial transforms at a slightly larger size 84 so the crop has room to operate. 85 """ 86 ops = [] 87 if training: 88 if use_clahe: 89 # Resize larger so RandomResizedCrop still sees enough context after CLAHE 90 ops.append(transforms.Resize((img_size + 32, img_size + 32))) 91 ops.append(CLAHETransform(clip_limit=2.0, tile_grid_size=(8, 8))) 92 ops += [ 93 transforms.RandomResizedCrop(img_size, scale=(0.8, 1.0), ratio=(0.9, 1.1)), 94 transforms.RandomHorizontalFlip(p=0.5), 95 transforms.RandomVerticalFlip(p=0.5), 96 transforms.RandomRotation(degrees=30), 97 transforms.ColorJitter(brightness=0.3, contrast=0.3, saturation=0.2, hue=0.02), 98 transforms.GaussianBlur(kernel_size=3, sigma=(0.1, 1.0)), 99 ] 100 else: 101 ops.append(transforms.Resize((img_size, img_size))) 102 if use_clahe: 103 ops.append(CLAHETransform(clip_limit=2.0, tile_grid_size=(8, 8))) 104 ops += [ 105 transforms.ToTensor(), 106 transforms.Normalize(mean=IMAGENET_MEAN, std=IMAGENET_STD), 107 ] 108 return transforms.Compose(ops) 109 110 111 def build_dataloaders( 112 train_paths, train_labels, 113 val_paths, val_labels, 114 test_paths, test_labels, 115 use_clahe: bool, 116 batch_size: int = 32, 117 num_workers: int = 4, 118 img_size: int = 224, 119 ): 120 """Create DataLoaders for all three splits. 121 122 The training DataLoader uses WeightedRandomSampler so that each class 123 is sampled at approximately equal frequency, counteracting class imbalance. 124 """ 125 train_ds = DRDataset(train_paths, train_labels, transform=build_transforms(use_clahe, training=True, img_size=img_size)) 126 val_ds = DRDataset(val_paths, val_labels, transform=build_transforms(use_clahe, training=False, img_size=img_size)) 127 test_ds = DRDataset(test_paths, test_labels, transform=build_transforms(use_clahe, training=False, img_size=img_size)) 128 129 # Per-sample weights: sqrt-inverse-frequency for moderate class balancing. 130 # Full inverse (1/count) causes over-prediction of minorities; sqrt gives a 131 # softer boost that retains enough majority-class signal. 132 labels_arr = np.array(train_labels) 133 class_counts = np.bincount(labels_arr, minlength=5) 134 class_sample_weights = 1.0 / np.sqrt(class_counts.astype(float)) 135 sample_weights = class_sample_weights[labels_arr] 136 sampler = WeightedRandomSampler( 137 weights=torch.from_numpy(sample_weights).float(), 138 num_samples=len(train_labels), 139 replacement=True, 140 ) 141 142 train_loader = DataLoader( 143 train_ds, batch_size=batch_size, sampler=sampler, 144 num_workers=num_workers, pin_memory=True, 145 persistent_workers=True, prefetch_factor=4, 146 ) 147 val_loader = DataLoader( 148 val_ds, batch_size=batch_size * 2, shuffle=False, 149 num_workers=num_workers, pin_memory=True, 150 persistent_workers=True, prefetch_factor=4, 151 ) 152 test_loader = DataLoader( 153 test_ds, batch_size=batch_size * 2, shuffle=False, 154 num_workers=num_workers, pin_memory=True, 155 persistent_workers=True, prefetch_factor=4, 156 ) 157 return train_loader, val_loader, test_loader