RandomResizedCrop modifications (#715)

* randomresizedmods

* lint checks

* test to randomrescrop added

* updates

* tests updated

* tests updated

* upd

* updates

* Update torchvision/transforms/transforms.py

Co-Authored-By: surgan12 <[email protected]>

* tests changed

* trvis

* travis

* fixes syntax

* ...

* flake fixes

* flake_fixes

* flake_fixes2

Author: surgan12

test/test_transforms.py

@@ -1,3 +1,4 @@
+from __future__ import division
 import torch
 import torchvision.transforms as transforms
 import torchvision.transforms.functional as F
@@ -130,6 +131,25 @@ def test_ten_crop(self):
                 assert len(results) == 10
                 assert expected_output == results
 
+    def test_randomresized_params(self):
+        height = random.randint(24, 32) * 2
+        width = random.randint(24, 32) * 2
+        img = torch.ones(3, height, width)
+        to_pil_image = transforms.ToPILImage()
+        img = to_pil_image(img)
+        size = 100
+        epsilon = 0.05
+        for i in range(10):
+            scale_min = round(random.random(), 2)
+            scale_range = (scale_min, scale_min + round(random.random(), 2))
+            aspect_min = round(random.random(), 2)
+            aspect_ratio_range = (aspect_min, aspect_min + round(random.random(), 2))
+            randresizecrop = transforms.RandomResizedCrop(size, scale_range, aspect_ratio_range)
+            _, _, h, w = randresizecrop.get_params(img, scale_range, aspect_ratio_range)
+            aspect_ratio_obtained = w / h
+            assert (min(aspect_ratio_range) - epsilon <= aspect_ratio_obtained <= max(aspect_ratio_range) + epsilon or
+                    aspect_ratio_obtained == 1.0)
+
     def test_resize(self):
         height = random.randint(24, 32) * 2
         width = random.randint(24, 32) * 2

torchvision/transforms/functional.py

@@ -376,8 +376,8 @@ def resized_crop(img, i, j, h, w, size, interpolation=Image.BILINEAR):
 
     Args:
         img (PIL Image): Image to be cropped.
-        i: Upper pixel coordinate.
-        j: Left pixel coordinate.
+        i: i in (i,j) i.e coordinates of the upper left corner
+        j: j in (i,j) i.e coordinates of the upper left corner
         h: Height of the cropped image.
         w: Width of the cropped image.
         size (sequence or int): Desired output size. Same semantics as ``resize``.

torchvision/transforms/transforms.py

@@ -543,7 +543,13 @@ class RandomResizedCrop(object):
     """
 
     def __init__(self, size, scale=(0.08, 1.0), ratio=(3. / 4., 4. / 3.), interpolation=Image.BILINEAR):
-        self.size = (size, size)
+        if isinstance(size, tuple):
+            self.size = size
+        else:
+            self.size = (size, size)
+        if (scale[0] > scale[1]) or (ratio[0] > ratio[1]):
+            warnings.warn("range should be of kind (min, max)")
+
         self.interpolation = interpolation
         self.scale = scale
         self.ratio = ratio
@@ -570,7 +576,7 @@ def get_params(img, scale, ratio):
             w = int(round(math.sqrt(target_area * aspect_ratio)))
             h = int(round(math.sqrt(target_area / aspect_ratio)))
 
-            if random.random() < 0.5:
+            if random.random() < 0.5 and min(ratio) <= (h / w) <= max(ratio):
                 w, h = h, w
 
             if w <= img.size[0] and h <= img.size[1]: