imageatlas 0.1.1__tar.gz → 0.1.2__tar.gz

{imageatlas-0.1.1 → imageatlas-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: imageatlas
-Version: 0.1.1
+Version: 0.1.2
 Summary: ImageAtlas: A toolkit for organizing, cleaning and analysing your image datasets.
 Author-email: Ahmad Javed <ahmadjaved97@gmail.com>
 Maintainer-email: Ahmad Javed <ahmadjaved97@gmail.com>

{imageatlas-0.1.1 → imageatlas-0.1.2}/imageatlas/__init__.py

@@ -2,7 +2,7 @@
 ImageAtlas: A toolkit for organizing, cleaning and analysing your image datasets.
 """
 
-__version__ = '0.1.1'
+__version__ = '0.1.2'
 
 
 # 1. High level API (The everything tool)

{imageatlas-0.1.1 → imageatlas-0.1.2}/imageatlas/features/batch.py

@@ -10,6 +10,8 @@ import warnings
 class BatchProcessor:
     """
     Handles batch processing of images through feature extractors.
+
+    Manages batching, device placement and memory cleanup.
     """
 
     def __init__(
@@ -20,6 +22,11 @@ class BatchProcessor:
     ):
         """
         Initialize batch processor.
+
+        Args:
+            batch_size: Number of images to process at once.
+            device: Device to use ('cpu', 'cuda', 'cuda:0', etc.)
+            clear_cache: Whether to clear GPU cache after each batch
         """
 
         self.batch_size = batch_size
@@ -50,8 +57,15 @@ class BatchProcessor:
     ):
         """
         Process a batch of extractors through the feature extractor.
-        TODO: use the correct batching method in the feature_extractors module.
+        Args:
+            images: List of PIL Images.
+            extractor: Feature extractor with extract_features method
+            return_numpy: Whether to return numpy array (vs torch tensor)
+        
+        Returns:
+            Array of feature vectors, shape (batch_size, feature_dim)
         """
+        # TODO: use the correct batching method in the feature_extractors module.
 
         if not images:
             return np.array([])
@@ -108,6 +122,14 @@ class BatchProcessor:
     ):
         """
         Estimate memory usage for a batch.
+
+        Args:
+            n_images: Number of images in a batch
+            feature_dim: Dimensions of feature vector
+            dtype: Data type of features
+
+        Returns:
+            Estimated memory in GB
         """
 
         bytes_per_element = np.dtype(dtype).itemsize

{imageatlas-0.1.1 → imageatlas-0.1.2}/imageatlas/features/cache.py

@@ -70,6 +70,12 @@ class HDF5Cache(FeatureCache):
     ):
         """
         Save features to HDF5 file.
+
+        Args:
+            features: Feature array, shape (n_samples, feature_dim)
+            filenames: List of filenames corresponding to features
+            metadata: Feature metadata
+            path: Path to save HDF5 file
         """
 
         # Make sure path has .h5 extension
@@ -115,6 +121,13 @@ class HDF5Cache(FeatureCache):
     ):
         """
         Load features from HDF5 file.
+
+        Args:
+            path: Path to HDF5 File
+            lazy: If True, return memory-mapped array instead of loading to RAM
+        
+        Returns:
+            Tuple of (features, filenames, metadata)
         """
 
         if not path.endswith(".h5"):
@@ -161,6 +174,14 @@ class HDF5Cache(FeatureCache):
     ):
         """
         Load a subset of features.
+
+        Args:
+            path: Path to HDF5 file
+            indices: Indices to load (if provided)
+            filenames: Filenames to load (if provided)
+        
+        Returns:
+            Tuple of (features, filenames)
         """
 
         if not path.endswith(".h5"):
@@ -193,6 +214,11 @@ class HDF5Cache(FeatureCache):
     ):
         """
         Append new features to existing cache.
+
+        Args:
+            path: Path to the HDF5 file
+            new_features: New features to append
+            new_filenames: Corresponding filenames
         """
 
         if not path.endswith(".h5"):
@@ -223,6 +249,12 @@ class HDF5Cache(FeatureCache):
     def get_feature_dict(self, path):
         """
         Load features as dictionary (for backward compatibility)
+
+        Args:
+            path: Path to HDF5 file
+        
+        Returns:
+            Dictionary mapping filenames to feature vectors
         """
         features, filenames, _ = self.load(path)
         return {fn: feat for fn, feat in zip(filenames, features)}
@@ -230,6 +262,12 @@ class HDF5Cache(FeatureCache):
     def get_info(self, path):
         """
         Get information about the cache without loading data.
+
+        Args:
+            path: Path to HDF5 file
+        
+        Returns:
+            Dictionary with cache information
         """
 
         if not path.endswith(".h5"):

{imageatlas-0.1.1 → imageatlas-0.1.2}/imageatlas/features/loaders.py

@@ -12,6 +12,8 @@ import warnings
 class ImageLoader:
     """
     Image loader with validation and error handling.
+
+    Handles corrupted images, format conversions, and EXIF orientations.
     """
     VALID_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.tiff', '.tif', '.webp'}
 
@@ -23,6 +25,11 @@ class ImageLoader:
     ):
         """
         Initialize image loader.
+
+        Args:
+            max_size: Optional maximum size (width, height) for images
+            convert_mode: PIL odel to covert images to ('RGB', 'L', etc.)
+            handle_exif: Whether to handle EXIF orientation
         """
 
         self.max_size = max_size
@@ -33,6 +40,12 @@ class ImageLoader:
     def validate_path(self, path):
         """
         Check if path is valid
+
+        Args:
+            path: Path to image file
+        
+        Returns:
+            True if valid, False otherwise
         """
         if not os.path.exists(path):
             return False
@@ -43,6 +56,12 @@ class ImageLoader:
     def load_image(self, path):
         """
         Load a single image.
+
+        Args:
+            path: Path to image file
+        
+        Returns:
+            PIL Image or None if loadig failed
         """
 
         try:
@@ -78,6 +97,12 @@ class ImageLoader:
     def load_batch(self, paths):
         """
         Load a batch of images.
+
+        Args:
+            paths: List of image paths
+        
+        Returns:
+            Tuple of (loaded_images, successful_paths, failed_paths)
         """
 
         images = []
@@ -97,6 +122,12 @@ class ImageLoader:
     def _handle_orientation(self, image):
         """
         Handle EXIF orientation tag.
+
+        Args:
+            image: PIL Image
+        
+        Returns:
+            Oriented image
         """
 
         try:
@@ -129,6 +160,12 @@ class ImageLoader:
     def _resize_if_needed(self, image):
         """
         Resize image if it exceeds max size.
+
+        Args:
+            image: PIL Image
+        
+        Returns:
+            Resized image
         """
         if self.max_size is None:
             return image
@@ -149,6 +186,14 @@ class ImageLoader:
     ):
         """
         Find all images in a directory.
+
+        Args:
+            directory: Directory to search
+            pattern: Glob pattern for filenames
+            recursive: Whether to search recursively
+        
+        Returns:
+            List of image paths
         """
         path = Path(directory)
 
@@ -180,6 +225,13 @@ class ImageLoader:
 
         """
         Create batches from a list of items.
+
+        Args:
+            items: List of items to batch
+            batch_size: Size of each batch
+        
+        Yeilds:
+            Batches of items
         """
 
         for i in range(0, len(items), batch_size):

{imageatlas-0.1.1 → imageatlas-0.1.2}/imageatlas/features/metadata.py

@@ -12,6 +12,9 @@ import json
 class FeatureMetadata:
     """
     Metadata for extracted features.
+
+    Tracks information about the feature extractionn process including
+    model details, extraction parameters, and statistics.
     """
 
     # Model information

{imageatlas-0.1.1 → imageatlas-0.1.2}/imageatlas/features/pipeline.py

@@ -17,6 +17,18 @@ from .metadata import FeatureMetadata
 class FeaturePipeline:
     """
     Main pipeline for feature extraction.
+
+    Handles batch processing, caching, progress tracking, and error recovery.
+
+    Example:
+        >>> from features import FeaturePipeline
+        >>> from feature_extractors import create_feature_extractor
+        >>> 
+        >>> extractor = create_feature_extractor('dinov2', device='cuda')
+        >>> pipeline = FeaturePipeline(extractor, batch_size=32)
+        >>> 
+        >>> result = pipeline.extract_from_directory('./images')
+        >>> pipeline.save('./features/features.h5')
     """
 
     def __init__(
@@ -30,6 +42,14 @@ class FeaturePipeline:
     ):
         """
         Initialize feature extraction pipeline.
+
+        Args:
+            extractor: Feature extractor (from feature_extractors module)
+            batch_size: Number of images to process at once
+            device: Device for processing ('cpu', 'cuda')
+            cache_backend: Cache backend to use ('hdf5')
+            max_image_size: Optional max size for images (width, height)
+            verbose: Whether to show progress bars
         """
 
         self.extractor = extractor
@@ -79,6 +99,16 @@ class FeaturePipeline:
 
         """
         Extract features from all images in a directory.
+
+        Args:
+            directory: Directory containing images
+            pattern: Glob pattern for filenames
+            recursive: Whether to search recursively
+            save_every: Save checkpoint every N images (optional)
+            save_path: Path for checkpoint saves (required if save_every is set)
+        
+        Returns:
+            Self for method chaining
         """
 
         # Find all images
@@ -112,6 +142,14 @@ class FeaturePipeline:
 
         """
         Extract features from a list of filepaths.
+
+        Args:
+            file_paths: List of image file paths
+            save_every: Save checkpoint every N images (optional)
+            save_path: Path for checkpoint saves (required if save_every is set)
+
+        Returns:
+            Self for method chaining
         """
 
         if save_every is not None and save_path is None:
@@ -223,6 +261,10 @@ class FeaturePipeline:
     def save(self, path, format='hdf5'):
         """
         Save extracted features to disk.
+
+        Args:
+            path: Path to save features
+            format: Format to use ('hdf5')
         """
 
         if self.features is None or self.metadata is None:
@@ -244,6 +286,11 @@ class FeaturePipeline:
     def load(self, path):
         """
         Load features from disk.
+
+        Args:
+            path: Path to feature cache
+        
+        Returns: Self for method chaining
         """
 
         self.features, self.filenames, self.metadata = self.cache.load(path)
@@ -271,6 +318,9 @@ class FeaturePipeline:
     def get_feature_dict(self):
         """
         Get features as dictionary
+
+        Returns:
+            Dictionary mapping filenames to feature vectors
         """
 
         if self.features is None:

{imageatlas-0.1.1 → imageatlas-0.1.2}/imageatlas.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: imageatlas
-Version: 0.1.1
+Version: 0.1.2
 Summary: ImageAtlas: A toolkit for organizing, cleaning and analysing your image datasets.
 Author-email: Ahmad Javed <ahmadjaved97@gmail.com>
 Maintainer-email: Ahmad Javed <ahmadjaved97@gmail.com>