[Datumaro] Disable lazy image caching by default (#876)

* Disable lazy image caching by default
* Deterministic cache test
* Add displacing image cache

datumaro/datumaro/util/image.py

@@ -6,6 +6,8 @@
 import cv2
 import numpy as np
 
+from datumaro.util.image_cache import ImageCache as _ImageCache
+
 
 def load_image(path):
     """
@@ -19,12 +21,35 @@ def load_image(path):
     return image
 
 class lazy_image:
-    def __init__(self, path, loader=load_image):
+    def __init__(self, path, loader=load_image, cache=None):
         self.path = path
         self.loader = loader
-        self.image = None
+
+        # Cache:
+        # - False: do not cache
+        # - None: use default (don't store in a class variable)
+        # - object: use this object as a cache
+        assert cache in [None, False] or isinstance(cache, object)
+        self.cache = cache
 
     def __call__(self):
-        if self.image is None:
-            self.image = self.loader(self.path)
-        return self.image
+        image = None
+        image_id = id(self) # path is not necessary hashable or a file path
+
+        cache = self._get_cache()
+        if cache is not None:
+            image = self._get_cache().get(image_id)
+
+        if image is None:
+            image = self.loader(self.path)
+            if cache is not None:
+                cache.push(image_id, image)
+        return image
+
+    def _get_cache(self):
+        cache = self.cache
+        if cache is None:
+            cache = _ImageCache.get_instance()
+        elif cache == False:
+            return None
+        return cache

datumaro/datumaro/util/image_cache.py

@@ -0,0 +1,38 @@
+from collections import OrderedDict
+
+
+_instance = None
+
+DEFAULT_CAPACITY = 1000
+
+class ImageCache:
+    @staticmethod
+    def get_instance():
+        global _instance
+        if _instance is None:
+            _instance = ImageCache()
+        return _instance
+
+    def __init__(self, capacity=DEFAULT_CAPACITY):
+        self.capacity = int(capacity)
+        self.items = OrderedDict()
+
+    def push(self, item_id, image):
+        if self.capacity <= len(self.items):
+            self.items.popitem(last=True)
+        self.items[item_id] = image
+
+    def get(self, item_id):
+        default = object()
+        item = self.items.get(item_id, default)
+        if item is default:
+            return None
+
+        self.items.move_to_end(item_id, last=False) # naive splay tree
+        return item
+
+    def size(self):
+        return len(self.items)
+
+    def clear(self):
+        self.items.clear()

datumaro/tests/test_images.py

@@ -0,0 +1,49 @@
+import numpy as np
+import os.path as osp
+from PIL import Image
+
+from unittest import TestCase
+
+from datumaro.util.test_utils import TestDir
+from datumaro.util.image import lazy_image
+from datumaro.util.image_cache import ImageCache
+
+
+class LazyImageTest(TestCase):
+    def test_cache_works(self):
+        with TestDir() as test_dir:
+            image = np.ones((100, 100, 3), dtype=np.uint8)
+            image = Image.fromarray(image).convert('RGB')
+
+            image_path = osp.join(test_dir.path, 'image.jpg')
+            image.save(image_path)
+
+            caching_loader = lazy_image(image_path, cache=None)
+            self.assertTrue(caching_loader() is caching_loader())
+
+            non_caching_loader = lazy_image(image_path, cache=False)
+            self.assertFalse(non_caching_loader() is non_caching_loader())
+
+class ImageCacheTest(TestCase):
+    def test_cache_fifo_displacement(self):
+        capacity = 2
+        cache = ImageCache(capacity)
+
+        loaders = [lazy_image(None, loader=lambda p: object(), cache=cache)
+            for _ in range(capacity + 1)]
+
+        first_request = [loader() for loader in loaders[1 : ]]
+        loaders[0]() # pop something from the cache
+
+        second_request = [loader() for loader in loaders[2 : ]]
+        second_request.insert(0, loaders[1]())
+
+        matches = sum([a is b for a, b in zip(first_request, second_request)])
+        self.assertEqual(matches, len(first_request) - 1)
+
+    def test_global_cache_is_accessible(self):
+        loader = lazy_image(None, loader=lambda p: object())
+
+        ImageCache.get_instance().clear()
+        self.assertTrue(loader() is loader())
+        self.assertEqual(ImageCache.get_instance().size(), 1)