def test_ToGray(fp):
img = read_img(fp)
result = transforms_cls.Compose([transforms_cls.ToGray()])(img)
assert result.dtype == img.dtype
assert result.ndim == 2
result = transforms_cls.Compose([transforms_cls.ToGray(output_channels=5)
])(img)
assert result.shape == (img.shape[0], img.shape[1], 5)
assert result.dtype == img.dtype
def test_RandomBrightness(fp):
img = read_img(fp)
result = transforms_cls.Compose([transforms_cls.RandomBrightness()])(img)
assert result.shape == img.shape
assert result.dtype == img.dtype
result = transforms_cls.Compose(
[transforms_cls.RandomBrightness(max_value=10)])(img)
assert result.shape == img.shape
assert result.dtype == img.dtype
if result.ndim == 2:
assert abs(float(result[0, 0]) - float(img[0, 0])) <= 10
else:
assert abs(float(result[0, 0, 0]) - float(img[0, 0, 0])) <= 10
def test_RandomContrast(fp):
img = read_img(fp)
result = transforms_cls.Compose([transforms_cls.RandomContrast()])(img)
assert result.shape == img.shape
assert result.dtype == img.dtype
result = transforms_cls.Compose(
[transforms_cls.RandomContrast(max_factor=1.2)])(img)
assert result.shape == img.shape
assert result.dtype == img.dtype
if result.ndim == 2:
assert abs(float(result[0, 0]) / float(img[0, 0])) <= 1.2
else:
assert abs(float(result[0, 0, 0]) / float(img[0, 0, 0])) <= 1.2
def load_data(traindir, valdir):
train_transform = T_cls.Compose([
T_cls.RandomHorizontalFlip(),
T_cls.RandomVerticalFlip(),
T_cls.ToTensor(),
T_cls.Normalize(),
])
val_transform = T_cls.Compose([
T_cls.ToTensor(),
T_cls.Normalize(),
])
dataset_train = ImageFolder(traindir, train_transform)
dataset_val = ImageFolder(valdir, val_transform)
return dataset_train, dataset_val
def test_GaussianBlur(fp):
img = read_img(fp)
result = transforms_cls.Compose([
transforms_cls.GaussianBlur(kernel_size=5)
])(img)
assert result.shape == img.shape
assert result.dtype == img.dtype
def test_RandomNoise(fp):
img = read_img(fp)
for item in ['gaussian', 'salt', 'pepper', 's&p']:
result = transforms_cls.Compose(
[transforms_cls.RandomNoise(mode=item)])(img)
assert result.shape == img.shape
assert result.dtype == img.dtype
def test_ToTensor(fp):
img = read_img(fp)
result = transforms_cls.Compose([
transforms_cls.ToTensor()
])(img)
assert type(result) == torch.Tensor
assert len(result.shape) == 3
assert result.shape[1:3] == img.shape[0:2]
def test_CenterCrop(fp):
img = read_img(fp)
result = transforms_cls.Compose([
transforms_cls.CenterCrop(300),
])(img)
assert result.shape[0:2] == (300,300)
assert result.dtype == img.dtype
result = transforms_cls.Compose([
transforms_cls.CenterCrop((500,300)),
])(img)
assert result.shape[0:2] == (500,300)
assert result.dtype == img.dtype
with pytest.raises(ValueError) as excinfo:
transforms_cls.CenterCrop(1000)(img)
assert 'the output_size should' in str(excinfo.value)
def test_Resize(fp):
img = read_img(fp)
result = transforms_cls.Compose([
transforms_cls.Resize(300),
transforms_cls.ToTensor(),
])(img)
assert result.shape[1:3] == torch.Size([300, 300])
assert type(result) == torch.Tensor
result = transforms_cls.Compose([
transforms_cls.Resize(833),
])(img)
assert result.shape[0:2] == (833, 833)
assert result.dtype == img.dtype
result = transforms_cls.Compose([
transforms_cls.Resize((500,300)),
])(img)
assert result.shape[0:2] == (500, 300)
assert result.dtype == img.dtype
def test_Normalize(fp):
img = read_img(fp)
channels = 1 if img.ndim==2 else img.shape[2]
mean = [img.mean()] if channels==1 else np.array(img.mean(axis=(0, 1))).tolist()
std = [img.std()] if channels==1 else np.array(img.std(axis=(0, 1))).tolist()
result = transforms_cls.Compose([
transforms_cls.ToTensor(),
transforms_cls.Normalize(mean, std)
])(img)
assert type(result) == torch.Tensor
assert len(result.shape) == 3
assert result.shape[1:3] == img.shape[0:2]
def _get_simclr_pipeline_transform(self):
gray = transforms_cls.ToGray()
# Mising Color Jitter (and others check paper, probably need to be handcrafted).
data_transforms = transforms_cls.Compose([
transforms_cls.RandomResizedCrop(crop_size=int(
self.input_shape[0] * .8),
target_size=self.input_shape[0]),
transforms_cls.RandomHorizontalFlip(), # Missing Color Jitter
#RandomApply([gray], p=0.8), #Should be random w some probability
transforms_cls.GaussianBlur(kernel_size=13),
transforms_cls.ToTensor()
])
return data_transforms
def test_Flip(fp):
img = read_img(fp)
result = transforms_cls.RandomFlip(p=0)(img)
assert result.dtype == img.dtype
assert result.shape[0:2] == img.shape[0:2]
if result.ndim == 2:
height, width = img.shape
assert result[0, 0] == img[0, 0]
else:
height, width, depth = img.shape
assert (result[0, 0, :] == img[0, 0, :]).any() == True
# tensor
result = transforms_cls.Compose(
[transforms_cls.RandomFlip(p=0.1),
transforms_cls.ToTensor()])(img)
assert type(result) == torch.Tensor
assert result.shape[1:3] == img.shape[0:2]
def test_Pad(fp):
img = read_img(fp)
# constant value
result = transforms_cls.Pad(10, fill=1)(img)
if result.ndim == 2:
assert result[0, 0] == 1
else:
assert result[0, 0, 0] == 1
# reflect value
result = transforms_cls.Pad(20, padding_mode='reflect')(img)
assert result.shape[0:2] == (img.shape[0] + 40, img.shape[1] + 40)
if result.ndim == 2:
assert result[0, 0] == img[20, 20]
else:
assert result[0, 0, 0] == img[20, 20, 0]
assert result.dtype == img.dtype
# all padding mode methods
for item in [
'reflect', 'edge', 'linear_ramp', 'maximum', 'mean', 'median',
'minimum', 'symmetric', 'wrap'
]:
# for item in ['edge']:
result = transforms_cls.Pad(10, padding_mode=item)(img)
assert result.dtype == img.dtype
assert result.shape[0:2] == (img.shape[0] + 20, img.shape[1] + 20)
result = transforms_cls.Pad((10, 20), padding_mode=item)(img)
assert result.shape[0:2] == (img.shape[0] + 40, img.shape[1] + 20)
assert result.dtype == img.dtype
result = transforms_cls.Pad((10, 20, 30, 40), padding_mode=item)(img)
assert result.shape[0:2] == (img.shape[0] + 60, img.shape[1] + 40)
assert result.dtype == img.dtype
result = transforms_cls.Compose(
[transforms_cls.Pad(10, fill=1),
transforms_cls.ToTensor()])(img)
assert type(result) == torch.Tensor
