File size: 20,813 Bytes
12fa055 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 |
"""
Data Loader Utilities
This module provides data loading utilities for different domains
(satellite, fashion, robotics) with support for few-shot and zero-shot learning.
"""
import torch
import torch.nn as nn
import numpy as np
from PIL import Image
import os
import json
from typing import List, Dict, Tuple, Optional
import random
from torch.utils.data import Dataset, DataLoader
import torchvision.transforms as transforms
from torchvision.transforms import functional as F
import cv2
class BaseDataLoader:
"""Base class for domain-specific data loaders."""
def __init__(self, data_dir: str, image_size: Tuple[int, int] = (512, 512)):
self.data_dir = data_dir
self.image_size = image_size
# Standard transforms
self.transform = transforms.Compose([
transforms.Resize(image_size),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
self.mask_transform = transforms.Compose([
transforms.Resize(image_size, interpolation=transforms.InterpolationMode.NEAREST),
transforms.ToTensor()
])
def load_image(self, image_path: str) -> torch.Tensor:
"""Load and preprocess image."""
image = Image.open(image_path).convert('RGB')
return self.transform(image)
def load_mask(self, mask_path: str) -> torch.Tensor:
"""Load and preprocess mask."""
mask = Image.open(mask_path).convert('L')
return self.mask_transform(mask)
def get_random_sample(self) -> Tuple[torch.Tensor, Dict[str, torch.Tensor]]:
"""Get a random sample from the dataset."""
raise NotImplementedError
def get_class_examples(self, class_name: str, num_examples: int) -> List[Tuple[torch.Tensor, torch.Tensor]]:
"""Get examples for a specific class."""
raise NotImplementedError
class SatelliteDataLoader(BaseDataLoader):
"""Data loader for satellite imagery segmentation."""
def __init__(self, data_dir: str, image_size: Tuple[int, int] = (512, 512)):
super().__init__(data_dir, image_size)
# Satellite-specific classes
self.classes = ["building", "road", "vegetation", "water"]
self.class_to_id = {cls: i for i, cls in enumerate(self.classes)}
# Load dataset structure
self.load_dataset_structure()
def load_dataset_structure(self):
"""Load dataset structure and file paths."""
self.images = []
self.masks = []
self.class_samples = {cls: [] for cls in self.classes}
# Assuming structure: data_dir/images/ and data_dir/masks/
images_dir = os.path.join(self.data_dir, "images")
masks_dir = os.path.join(self.data_dir, "masks")
if not os.path.exists(images_dir) or not os.path.exists(masks_dir):
# Create dummy data for demonstration
self.create_dummy_data()
return
# Load real data
for filename in os.listdir(images_dir):
if filename.endswith(('.jpg', '.png', '.tif')):
image_path = os.path.join(images_dir, filename)
mask_path = os.path.join(masks_dir, filename.replace('.jpg', '_mask.png'))
if os.path.exists(mask_path):
self.images.append(image_path)
self.masks.append(mask_path)
# Categorize by class (simplified)
self.categorize_sample(image_path, mask_path)
def create_dummy_data(self):
"""Create dummy satellite data for demonstration."""
print("Creating dummy satellite data...")
# Create dummy directory structure
os.makedirs(os.path.join(self.data_dir, "images"), exist_ok=True)
os.makedirs(os.path.join(self.data_dir, "masks"), exist_ok=True)
# Generate dummy images and masks
for i in range(100):
# Create dummy image (satellite-like)
image = np.random.randint(50, 200, (512, 512, 3), dtype=np.uint8)
# Add some structure to make it look like satellite imagery
# Buildings (rectangular shapes)
for _ in range(5):
x, y = np.random.randint(0, 400), np.random.randint(0, 400)
w, h = np.random.randint(20, 80), np.random.randint(20, 80)
image[y:y+h, x:x+w] = np.random.randint(100, 150, 3)
# Roads (linear structures)
for _ in range(3):
x, y = np.random.randint(0, 512), np.random.randint(0, 512)
length = np.random.randint(50, 150)
angle = np.random.uniform(0, 2*np.pi)
for j in range(length):
px = int(x + j * np.cos(angle))
py = int(y + j * np.sin(angle))
if 0 <= px < 512 and 0 <= py < 512:
image[py, px] = [80, 80, 80]
# Save image
image_path = os.path.join(self.data_dir, "images", f"satellite_{i:03d}.jpg")
Image.fromarray(image).save(image_path)
# Create corresponding mask
mask = np.zeros((512, 512), dtype=np.uint8)
# Add building masks
for _ in range(3):
x, y = np.random.randint(0, 400), np.random.randint(0, 400)
w, h = np.random.randint(20, 80), np.random.randint(20, 80)
mask[y:y+h, x:x+w] = 1 # Building class
# Add road masks
for _ in range(2):
x, y = np.random.randint(0, 512), np.random.randint(0, 512)
length = np.random.randint(50, 150)
angle = np.random.uniform(0, 2*np.pi)
for j in range(length):
px = int(x + j * np.cos(angle))
py = int(y + j * np.sin(angle))
if 0 <= px < 512 and 0 <= py < 512:
mask[py, px] = 2 # Road class
# Save mask
mask_path = os.path.join(self.data_dir, "masks", f"satellite_{i:03d}_mask.png")
Image.fromarray(mask * 85).save(mask_path) # Scale for visibility
# Add to lists
self.images.append(image_path)
self.masks.append(mask_path)
# Categorize
self.categorize_sample(image_path, mask_path)
def categorize_sample(self, image_path: str, mask_path: str):
"""Categorize sample by dominant class."""
mask = np.array(Image.open(mask_path))
# Count pixels for each class
class_counts = {}
for i, class_name in enumerate(self.classes):
class_counts[class_name] = np.sum(mask == i)
# Find dominant class
dominant_class = max(class_counts.items(), key=lambda x: x[1])[0]
self.class_samples[dominant_class].append((image_path, mask_path))
def get_random_query(self, class_name: str) -> Tuple[torch.Tensor, torch.Tensor]:
"""Get a random query image and mask for a specific class."""
if class_name not in self.class_samples or not self.class_samples[class_name]:
# Fallback to any available sample
idx = random.randint(0, len(self.images) - 1)
image = self.load_image(self.images[idx])
mask = self.load_mask(self.masks[idx])
return image, mask
# Get random sample from specified class
image_path, mask_path = random.choice(self.class_samples[class_name])
image = self.load_image(image_path)
mask = self.load_mask(mask_path)
return image, mask
def get_class_examples(self, class_name: str, num_examples: int) -> List[Tuple[torch.Tensor, torch.Tensor]]:
"""Get examples for a specific class."""
examples = []
if class_name in self.class_samples:
available_samples = self.class_samples[class_name]
selected_samples = random.sample(available_samples, min(num_examples, len(available_samples)))
for image_path, mask_path in selected_samples:
image = self.load_image(image_path)
mask = self.load_mask(mask_path)
examples.append((image, mask))
return examples
class FashionDataLoader(BaseDataLoader):
"""Data loader for fashion segmentation."""
def __init__(self, data_dir: str, image_size: Tuple[int, int] = (512, 512)):
super().__init__(data_dir, image_size)
# Fashion-specific classes
self.classes = ["shirt", "pants", "dress", "shoes"]
self.class_to_id = {cls: i for i, cls in enumerate(self.classes)}
# Load dataset structure
self.load_dataset_structure()
def load_dataset_structure(self):
"""Load dataset structure and file paths."""
self.images = []
self.masks = []
self.class_samples = {cls: [] for cls in self.classes}
# Assuming structure: data_dir/images/ and data_dir/masks/
images_dir = os.path.join(self.data_dir, "images")
masks_dir = os.path.join(self.data_dir, "masks")
if not os.path.exists(images_dir) or not os.path.exists(masks_dir):
# Create dummy data for demonstration
self.create_dummy_data()
return
# Load real data
for filename in os.listdir(images_dir):
if filename.endswith(('.jpg', '.png')):
image_path = os.path.join(images_dir, filename)
mask_path = os.path.join(masks_dir, filename.replace('.jpg', '_mask.png'))
if os.path.exists(mask_path):
self.images.append(image_path)
self.masks.append(mask_path)
# Categorize by class
self.categorize_sample(image_path, mask_path)
def create_dummy_data(self):
"""Create dummy fashion data for demonstration."""
print("Creating dummy fashion data...")
# Create dummy directory structure
os.makedirs(os.path.join(self.data_dir, "images"), exist_ok=True)
os.makedirs(os.path.join(self.data_dir, "masks"), exist_ok=True)
# Generate dummy images and masks
for i in range(100):
# Create dummy image (fashion-like)
image = np.random.randint(200, 255, (512, 512, 3), dtype=np.uint8)
# Add fashion items
class_id = i % len(self.classes)
if class_id == 0: # Shirt
# Create shirt-like shape
center_x, center_y = 256, 256
width, height = 150, 200
image[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = [100, 150, 200]
elif class_id == 1: # Pants
# Create pants-like shape
center_x, center_y = 256, 300
width, height = 120, 180
image[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = [50, 100, 150]
elif class_id == 2: # Dress
# Create dress-like shape
center_x, center_y = 256, 250
width, height = 140, 220
image[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = [200, 100, 150]
else: # Shoes
# Create shoes-like shape
center_x, center_y = 256, 400
width, height = 100, 60
image[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = [80, 80, 80]
# Save image
image_path = os.path.join(self.data_dir, "images", f"fashion_{i:03d}.jpg")
Image.fromarray(image).save(image_path)
# Create corresponding mask
mask = np.zeros((512, 512), dtype=np.uint8)
# Add mask for the fashion item
if class_id == 0: # Shirt
center_x, center_y = 256, 256
width, height = 150, 200
mask[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = 1
elif class_id == 1: # Pants
center_x, center_y = 256, 300
width, height = 120, 180
mask[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = 2
elif class_id == 2: # Dress
center_x, center_y = 256, 250
width, height = 140, 220
mask[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = 3
else: # Shoes
center_x, center_y = 256, 400
width, height = 100, 60
mask[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = 4
# Save mask
mask_path = os.path.join(self.data_dir, "masks", f"fashion_{i:03d}_mask.png")
Image.fromarray(mask * 51).save(mask_path) # Scale for visibility
# Add to lists
self.images.append(image_path)
self.masks.append(mask_path)
# Categorize
self.categorize_sample(image_path, mask_path)
def categorize_sample(self, image_path: str, mask_path: str):
"""Categorize sample by dominant class."""
mask = np.array(Image.open(mask_path))
# Count pixels for each class
class_counts = {}
for i, class_name in enumerate(self.classes):
class_counts[class_name] = np.sum(mask == (i + 1)) # +1 because 0 is background
# Find dominant class
dominant_class = max(class_counts.items(), key=lambda x: x[1])[0]
self.class_samples[dominant_class].append((image_path, mask_path))
def get_test_sample(self) -> Tuple[torch.Tensor, Dict[str, torch.Tensor]]:
"""Get a random test sample with ground truth masks."""
idx = random.randint(0, len(self.images) - 1)
image = self.load_image(self.images[idx])
mask = self.load_mask(self.masks[idx])
# Convert single mask to multi-class dictionary
ground_truth = {}
for i, class_name in enumerate(self.classes):
class_mask = (mask == (i + 1)).float() # +1 because 0 is background
ground_truth[class_name] = class_mask
return image, ground_truth
class RoboticsDataLoader(BaseDataLoader):
"""Data loader for robotics segmentation."""
def __init__(self, data_dir: str, image_size: Tuple[int, int] = (512, 512)):
super().__init__(data_dir, image_size)
# Robotics-specific classes
self.classes = ["robot", "tool", "safety"]
self.class_to_id = {cls: i for i, cls in enumerate(self.classes)}
# Load dataset structure
self.load_dataset_structure()
def load_dataset_structure(self):
"""Load dataset structure and file paths."""
self.images = []
self.masks = []
self.class_samples = {cls: [] for cls in self.classes}
# Assuming structure: data_dir/images/ and data_dir/masks/
images_dir = os.path.join(self.data_dir, "images")
masks_dir = os.path.join(self.data_dir, "masks")
if not os.path.exists(images_dir) or not os.path.exists(masks_dir):
# Create dummy data for demonstration
self.create_dummy_data()
return
# Load real data
for filename in os.listdir(images_dir):
if filename.endswith(('.jpg', '.png')):
image_path = os.path.join(images_dir, filename)
mask_path = os.path.join(masks_dir, filename.replace('.jpg', '_mask.png'))
if os.path.exists(mask_path):
self.images.append(image_path)
self.masks.append(mask_path)
# Categorize by class
self.categorize_sample(image_path, mask_path)
def create_dummy_data(self):
"""Create dummy robotics data for demonstration."""
print("Creating dummy robotics data...")
# Create dummy directory structure
os.makedirs(os.path.join(self.data_dir, "images"), exist_ok=True)
os.makedirs(os.path.join(self.data_dir, "masks"), exist_ok=True)
# Generate dummy images and masks
for i in range(100):
# Create dummy image (robotics-like)
image = np.random.randint(50, 150, (512, 512, 3), dtype=np.uint8)
# Add robotics elements
class_id = i % len(self.classes)
if class_id == 0: # Robot
# Create robot-like shape
center_x, center_y = 256, 256
width, height = 120, 160
image[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = [100, 100, 100]
elif class_id == 1: # Tool
# Create tool-like shape
center_x, center_y = 256, 256
width, height = 80, 120
image[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = [150, 100, 50]
else: # Safety equipment
# Create safety equipment-like shape
center_x, center_y = 256, 256
width, height = 100, 100
image[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = [200, 200, 50]
# Save image
image_path = os.path.join(self.data_dir, "images", f"robotics_{i:03d}.jpg")
Image.fromarray(image).save(image_path)
# Create corresponding mask
mask = np.zeros((512, 512), dtype=np.uint8)
# Add mask for the robotics element
if class_id == 0: # Robot
center_x, center_y = 256, 256
width, height = 120, 160
mask[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = 1
elif class_id == 1: # Tool
center_x, center_y = 256, 256
width, height = 80, 120
mask[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = 2
else: # Safety equipment
center_x, center_y = 256, 256
width, height = 100, 100
mask[center_y-height//2:center_y+height//2, center_x-width//2:center_x+width//2] = 3
# Save mask
mask_path = os.path.join(self.data_dir, "masks", f"robotics_{i:03d}_mask.png")
Image.fromarray(mask * 85).save(mask_path) # Scale for visibility
# Add to lists
self.images.append(image_path)
self.masks.append(mask_path)
# Categorize
self.categorize_sample(image_path, mask_path)
def categorize_sample(self, image_path: str, mask_path: str):
"""Categorize sample by dominant class."""
mask = np.array(Image.open(mask_path))
# Count pixels for each class
class_counts = {}
for i, class_name in enumerate(self.classes):
class_counts[class_name] = np.sum(mask == (i + 1)) # +1 because 0 is background
# Find dominant class
dominant_class = max(class_counts.items(), key=lambda x: x[1])[0]
self.class_samples[dominant_class].append((image_path, mask_path))
def get_test_sample(self) -> Tuple[torch.Tensor, Dict[str, torch.Tensor]]:
"""Get a random test sample with ground truth masks."""
idx = random.randint(0, len(self.images) - 1)
image = self.load_image(self.images[idx])
mask = self.load_mask(self.masks[idx])
# Convert single mask to multi-class dictionary
ground_truth = {}
for i, class_name in enumerate(self.classes):
class_mask = (mask == (i + 1)).float() # +1 because 0 is background
ground_truth[class_name] = class_mask
return image, ground_truth |