def test_gmsd_modes(x, y, device: str) -> None:
for reduction in ['mean', 'sum', 'none']:
gmsd(x.to(device), y.to(device), reduction=reduction)
for reduction in ['DEADBEEF', 'random']:
with pytest.raises(ValueError):
gmsd(x.to(device), y.to(device), reduction=reduction)
def test_gmsd_modes(prediction: torch.Tensor, target: torch.Tensor, device: str) -> None:
for reduction in ['mean', 'sum', 'none']:
gmsd(prediction.to(device), target.to(device), reduction=reduction)
for reduction in ['DEADBEEF', 'random']:
with pytest.raises(KeyError):
gmsd(prediction.to(device), target.to(device), reduction=reduction)
def test_gmsd_supports_different_data_ranges(prediction: torch.Tensor, target: torch.Tensor, device: str) -> None:
prediction_255 = (prediction * 255).type(torch.uint8)
target_255 = (target * 255).type(torch.uint8)
measure = gmsd(prediction.to(device), target.to(device))
measure_255 = gmsd(prediction_255.to(device), target_255.to(device), data_range=255)
diff = torch.abs(measure_255 - measure)
assert diff <= 1e-4, f'Result for same tensor with different data_range should be the same, got {diff}'
def test_gmsd_supports_different_data_ranges(x, y, data_range, device: str) -> None:
x_scaled = (x * data_range).type(torch.uint8)
y_scaled = (y * data_range).type(torch.uint8)
measure_scaled = gmsd(x_scaled.to(device), y_scaled.to(device), data_range=data_range)
measure = gmsd(
x_scaled.to(device) / float(data_range),
y_scaled.to(device) / float(data_range),
data_range=1.0
)
diff = torch.abs(measure_scaled - measure)
assert diff <= 1e-6, f'Result for same tensor with different data_range should be the same, got {diff}'
def test_gmsd_supports_different_data_ranges(
prediction: torch.Tensor, target: torch.Tensor, data_range, device: str) -> None:
prediction_scaled = (prediction * data_range).type(torch.uint8)
target_scaled = (target * data_range).type(torch.uint8)
measure_scaled = gmsd(prediction_scaled.to(device), target_scaled.to(device), data_range=data_range)
measure = gmsd(
prediction_scaled.to(device) / float(data_range),
target_scaled.to(device) / float(data_range),
data_range=1.0
)
diff = torch.abs(measure_scaled - measure)
assert diff <= 1e-6, f'Result for same tensor with different data_range should be the same, got {diff}'
def test_gmsd_compare_with_matlab(input_images_score: Tuple[torch.Tensor,
torch.Tensor,
torch.Tensor],
device: str) -> None:
x, y, y_value = input_images_score
score = gmsd(x=x.to(device), y=y.to(device), data_range=255)
assert torch.isclose(score, y_value.to(score)), f'The estimated value must be equal to MATLAB provided one, ' \
f'got {score.item():.8f}, while MATLAB equals {y_value}'
def test_gmsd_supports_greyscale_tensors(device: str) -> None:
y = torch.ones(2, 1, 96, 96)
x = torch.zeros(2, 1, 96, 96)
gmsd(x.to(device), y.to(device))
def test_gmsd_supports_greyscale_tensors(device: str) -> None:
target = torch.ones(2, 1, 96, 96)
prediction = torch.zeros(2, 1, 96, 96)
gmsd(prediction.to(device), target.to(device))
def test_gmsd_raises_if_tensors_have_different_types(target: torch.Tensor, device: str) -> None:
wrong_type_predictions = [list(range(10)), np.arange(10)]
for wrong_type_prediction in wrong_type_predictions:
with pytest.raises(AssertionError):
gmsd(wrong_type_prediction, target.to(device))
def test_gmsd_forward(prediction: torch.Tensor, target: torch.Tensor, device: str) -> None:
gmsd(prediction.to(device), target.to(device))
def test_gmsd_zero_for_equal_tensors(prediction: torch.Tensor, device: str) -> None:
target = prediction.clone()
measure = gmsd(prediction.to(device), target.to(device))
assert measure.abs() <= 1e-6, f'GMSD for equal tensors must be 0, got {measure}'
def test_gmsd_preserves_dtype(x, y, dtype, device: str) -> None:
output = gmsd(x.to(device=device, dtype=dtype),
y.to(device=device, dtype=dtype))
assert output.dtype == dtype
def main():
# Read RGB image and it's noisy version
x = torch.tensor(imread('tests/assets/i01_01_5.bmp')).permute(2, 0,
1) / 255.
y = torch.tensor(imread('tests/assets/I01.BMP')).permute(2, 0, 1) / 255.
if torch.cuda.is_available():
# Move to GPU to make computaions faster
x = x.cuda()
y = y.cuda()
# To compute BRISQUE score as a measure, use lower case function from the library
brisque_index: torch.Tensor = piq.brisque(x,
data_range=1.,
reduction='none')
# In order to use BRISQUE as a loss function, use corresponding PyTorch module.
# Note: the back propagation is not available using torch==1.5.0.
# Update the environment with latest torch and torchvision.
brisque_loss: torch.Tensor = piq.BRISQUELoss(data_range=1.,
reduction='none')(x)
print(
f"BRISQUE index: {brisque_index.item():0.4f}, loss: {brisque_loss.item():0.4f}"
)
# To compute Content score as a loss function, use corresponding PyTorch module
# By default VGG16 model is used, but any feature extractor model is supported.
# Don't forget to adjust layers names accordingly. Features from different layers can be weighted differently.
# Use weights parameter. See other options in class docstring.
content_loss = piq.ContentLoss(feature_extractor="vgg16",
layers=("relu3_3", ),
reduction='none')(x, y)
print(f"ContentLoss: {content_loss.item():0.4f}")
# To compute DISTS as a loss function, use corresponding PyTorch module
# By default input images are normalized with ImageNet statistics before forwarding through VGG16 model.
# If there is no need to normalize the data, use mean=[0.0, 0.0, 0.0] and std=[1.0, 1.0, 1.0].
dists_loss = piq.DISTS(reduction='none')(x, y)
print(f"DISTS: {dists_loss.item():0.4f}")
# To compute FSIM as a measure, use lower case function from the library
fsim_index: torch.Tensor = piq.fsim(x, y, data_range=1., reduction='none')
# In order to use FSIM as a loss function, use corresponding PyTorch module
fsim_loss = piq.FSIMLoss(data_range=1., reduction='none')(x, y)
print(
f"FSIM index: {fsim_index.item():0.4f}, loss: {fsim_loss.item():0.4f}")
# To compute GMSD as a measure, use lower case function from the library
# This is port of MATLAB version from the authors of original paper.
# In any case it should me minimized. Usually values of GMSD lie in [0, 0.35] interval.
gmsd_index: torch.Tensor = piq.gmsd(x, y, data_range=1., reduction='none')
# In order to use GMSD as a loss function, use corresponding PyTorch module:
gmsd_loss: torch.Tensor = piq.GMSDLoss(data_range=1., reduction='none')(x,
y)
print(
f"GMSD index: {gmsd_index.item():0.4f}, loss: {gmsd_loss.item():0.4f}")
# To compute HaarPSI as a measure, use lower case function from the library
# This is port of MATLAB version from the authors of original paper.
haarpsi_index: torch.Tensor = piq.haarpsi(x,
y,
data_range=1.,
reduction='none')
# In order to use HaarPSI as a loss function, use corresponding PyTorch module
haarpsi_loss: torch.Tensor = piq.HaarPSILoss(data_range=1.,
reduction='none')(x, y)
print(
f"HaarPSI index: {haarpsi_index.item():0.4f}, loss: {haarpsi_loss.item():0.4f}"
)
# To compute LPIPS as a loss function, use corresponding PyTorch module
lpips_loss: torch.Tensor = piq.LPIPS(reduction='none')(x, y)
print(f"LPIPS: {lpips_loss.item():0.4f}")
# To compute MDSI as a measure, use lower case function from the library
mdsi_index: torch.Tensor = piq.mdsi(x, y, data_range=1., reduction='none')
# In order to use MDSI as a loss function, use corresponding PyTorch module
mdsi_loss: torch.Tensor = piq.MDSILoss(data_range=1., reduction='none')(x,
y)
print(
f"MDSI index: {mdsi_index.item():0.4f}, loss: {mdsi_loss.item():0.4f}")
# To compute MS-SSIM index as a measure, use lower case function from the library:
ms_ssim_index: torch.Tensor = piq.multi_scale_ssim(x, y, data_range=1.)
# In order to use MS-SSIM as a loss function, use corresponding PyTorch module:
ms_ssim_loss = piq.MultiScaleSSIMLoss(data_range=1., reduction='none')(x,
y)
print(
f"MS-SSIM index: {ms_ssim_index.item():0.4f}, loss: {ms_ssim_loss.item():0.4f}"
)
# To compute Multi-Scale GMSD as a measure, use lower case function from the library
# It can be used both as a measure and as a loss function. In any case it should me minimized.
# By defualt scale weights are initialized with values from the paper.
# You can change them by passing a list of 4 variables to scale_weights argument during initialization
# Note that input tensors should contain images with height and width equal 2 ** number_of_scales + 1 at least.
ms_gmsd_index: torch.Tensor = piq.multi_scale_gmsd(x,
y,
data_range=1.,
chromatic=True,
reduction='none')
# In order to use Multi-Scale GMSD as a loss function, use corresponding PyTorch module
ms_gmsd_loss: torch.Tensor = piq.MultiScaleGMSDLoss(chromatic=True,
data_range=1.,
reduction='none')(x, y)
print(
f"MS-GMSDc index: {ms_gmsd_index.item():0.4f}, loss: {ms_gmsd_loss.item():0.4f}"
)
# To compute PSNR as a measure, use lower case function from the library.
psnr_index = piq.psnr(x, y, data_range=1., reduction='none')
print(f"PSNR index: {psnr_index.item():0.4f}")
# To compute PieAPP as a loss function, use corresponding PyTorch module:
pieapp_loss: torch.Tensor = piq.PieAPP(reduction='none', stride=32)(x, y)
print(f"PieAPP loss: {pieapp_loss.item():0.4f}")
# To compute SSIM index as a measure, use lower case function from the library:
ssim_index = piq.ssim(x, y, data_range=1.)
# In order to use SSIM as a loss function, use corresponding PyTorch module:
ssim_loss: torch.Tensor = piq.SSIMLoss(data_range=1.)(x, y)
print(
f"SSIM index: {ssim_index.item():0.4f}, loss: {ssim_loss.item():0.4f}")
# To compute Style score as a loss function, use corresponding PyTorch module:
# By default VGG16 model is used, but any feature extractor model is supported.
# Don't forget to adjust layers names accordingly. Features from different layers can be weighted differently.
# Use weights parameter. See other options in class docstring.
style_loss = piq.StyleLoss(feature_extractor="vgg16",
layers=("relu3_3", ))(x, y)
print(f"Style: {style_loss.item():0.4f}")
# To compute TV as a measure, use lower case function from the library:
tv_index: torch.Tensor = piq.total_variation(x)
# In order to use TV as a loss function, use corresponding PyTorch module:
tv_loss: torch.Tensor = piq.TVLoss(reduction='none')(x)
print(f"TV index: {tv_index.item():0.4f}, loss: {tv_loss.item():0.4f}")
# To compute VIF as a measure, use lower case function from the library:
vif_index: torch.Tensor = piq.vif_p(x, y, data_range=1.)
# In order to use VIF as a loss function, use corresponding PyTorch class:
vif_loss: torch.Tensor = piq.VIFLoss(sigma_n_sq=2.0, data_range=1.)(x, y)
print(f"VIFp index: {vif_index.item():0.4f}, loss: {vif_loss.item():0.4f}")
# To compute VSI score as a measure, use lower case function from the library:
vsi_index: torch.Tensor = piq.vsi(x, y, data_range=1.)
# In order to use VSI as a loss function, use corresponding PyTorch module:
vsi_loss: torch.Tensor = piq.VSILoss(data_range=1.)(x, y)
print(f"VSI index: {vsi_index.item():0.4f}, loss: {vsi_loss.item():0.4f}")
def test_gmsd_fails_for_incorrect_data_range(prediction: torch.Tensor, target: torch.Tensor, device: str) -> None:
# Scale to [0, 255]
prediction_scaled = (prediction * 255).type(torch.uint8)
target_scaled = (target * 255).type(torch.uint8)
with pytest.raises(AssertionError):
gmsd(prediction_scaled.to(device), target_scaled.to(device), data_range=1.0)
def test_gmsd_fails_for_incorrect_data_range(x, y, device: str) -> None:
# Scale to [0, 255]
x_scaled = (x * 255).type(torch.uint8)
y_scaled = (y * 255).type(torch.uint8)
with pytest.raises(AssertionError):
gmsd(x_scaled.to(device), y_scaled.to(device), data_range=1.0)
def test_gmsd_forward(x, y, device: str) -> None:
gmsd(x.to(device), y.to(device))
def test_gmsd_raises_if_tensors_have_different_types(y, device: str) -> None:
wrong_type_x = [list(range(10)), np.arange(10)]
for wrong_type_x in wrong_type_x:
with pytest.raises(AssertionError):
gmsd(wrong_type_x, y.to(device))
def test_gmsd_zero_for_equal_tensors(x, device: str) -> None:
y = x.clone()
measure = gmsd(x.to(device), y.to(device))
assert measure.abs() <= 1e-6, f'GMSD for equal tensors must be 0, got {measure}'
