Skip to content

Test for checking non mutating behaviour of tensor transforms #1656

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 12, 2019
Merged

Test for checking non mutating behaviour of tensor transforms #1656

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1b1d46b
out_place checks
surgan12 Dec 11, 2019
02375e1
lint ups
surgan12 Dec 11, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 16 additions & 1 deletion test/test_functional_tensor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,20 +12,25 @@ class Tester(unittest.TestCase):

def test_vflip(self):
img_tensor = torch.randn(3, 16, 16)
img_tensor_clone = img_tensor.clone()
vflipped_img = F_t.vflip(img_tensor)
vflipped_img_again = F_t.vflip(vflipped_img)
self.assertEqual(vflipped_img.shape, img_tensor.shape)
self.assertTrue(torch.equal(img_tensor, vflipped_img_again))
self.assertTrue(torch.equal(img_tensor, img_tensor_clone))

def test_hflip(self):
img_tensor = torch.randn(3, 16, 16)
img_tensor_clone = img_tensor.clone()
hflipped_img = F_t.hflip(img_tensor)
hflipped_img_again = F_t.hflip(hflipped_img)
self.assertEqual(hflipped_img.shape, img_tensor.shape)
self.assertTrue(torch.equal(img_tensor, hflipped_img_again))
self.assertTrue(torch.equal(img_tensor, img_tensor_clone))

def test_crop(self):
img_tensor = torch.randint(0, 255, (3, 16, 16), dtype=torch.uint8)
img_tensor_clone = img_tensor.clone()
top = random.randint(0, 15)
left = random.randint(0, 15)
height = random.randint(1, 16 - top)
Expand All @@ -34,7 +39,7 @@ def test_crop(self):
img_PIL = transforms.ToPILImage()(img_tensor)
img_PIL_cropped = F.crop(img_PIL, top, left, height, width)
img_cropped_GT = transforms.ToTensor()(img_PIL_cropped)

self.assertTrue(torch.equal(img_tensor, img_tensor_clone))
self.assertTrue(torch.equal(img_cropped, (img_cropped_GT * 255).to(torch.uint8)),
"functional_tensor crop not working")

Expand All @@ -54,6 +59,7 @@ def test_adjustments(self):
img = torch.randint(0, 256, shape, dtype=torch.uint8)

factor = 3 * torch.rand(1)
img_clone = img.clone()
for f, ft in fns:

ft_img = ft(img, factor)
Expand All @@ -68,23 +74,29 @@ def test_adjustments(self):
# difference in values caused by (at most 5) truncations.
max_diff = (ft_img - f_img).abs().max()
self.assertLess(max_diff, 5 / 255 + 1e-5)
self.assertTrue(torch.equal(img, img_clone))

def test_rgb_to_grayscale(self):
img_tensor = torch.randint(0, 255, (3, 16, 16), dtype=torch.uint8)
img_tensor_clone = img_tensor.clone()
grayscale_tensor = F_t.rgb_to_grayscale(img_tensor).to(int)
grayscale_pil_img = torch.tensor(np.array(F.to_grayscale(F.to_pil_image(img_tensor)))).to(int)
max_diff = (grayscale_tensor - grayscale_pil_img).abs().max()
self.assertLess(max_diff, 1.0001)
self.assertTrue(torch.equal(img_tensor, img_tensor_clone))

def test_center_crop(self):
img_tensor = torch.randint(0, 255, (1, 32, 32), dtype=torch.uint8)
img_tensor_clone = img_tensor.clone()
cropped_tensor = F_t.center_crop(img_tensor, [10, 10])
cropped_pil_image = F.center_crop(transforms.ToPILImage()(img_tensor), [10, 10])
cropped_pil_tensor = (transforms.ToTensor()(cropped_pil_image) * 255).to(torch.uint8)
self.assertTrue(torch.equal(cropped_tensor, cropped_pil_tensor))
self.assertTrue(torch.equal(img_tensor, img_tensor_clone))

def test_five_crop(self):
img_tensor = torch.randint(0, 255, (1, 32, 32), dtype=torch.uint8)
img_tensor_clone = img_tensor.clone()
cropped_tensor = F_t.five_crop(img_tensor, [10, 10])
cropped_pil_image = F.five_crop(transforms.ToPILImage()(img_tensor), [10, 10])
self.assertTrue(torch.equal(cropped_tensor[0],
Expand All @@ -97,9 +109,11 @@ def test_five_crop(self):
(transforms.ToTensor()(cropped_pil_image[3]) * 255).to(torch.uint8)))
self.assertTrue(torch.equal(cropped_tensor[4],
(transforms.ToTensor()(cropped_pil_image[4]) * 255).to(torch.uint8)))
self.assertTrue(torch.equal(img_tensor, img_tensor_clone))

def test_ten_crop(self):
img_tensor = torch.randint(0, 255, (1, 32, 32), dtype=torch.uint8)
img_tensor_clone = img_tensor.clone()
cropped_tensor = F_t.ten_crop(img_tensor, [10, 10])
cropped_pil_image = F.ten_crop(transforms.ToPILImage()(img_tensor), [10, 10])
self.assertTrue(torch.equal(cropped_tensor[0],
Expand All @@ -122,6 +136,7 @@ def test_ten_crop(self):
(transforms.ToTensor()(cropped_pil_image[8]) * 255).to(torch.uint8)))
self.assertTrue(torch.equal(cropped_tensor[9],
(transforms.ToTensor()(cropped_pil_image[9]) * 255).to(torch.uint8)))
self.assertTrue(torch.equal(img_tensor, img_tensor_clone))


if __name__ == '__main__':
Expand Down