def __init__(self, config: dict) -> None:
logger.debug("Initializing %s", self.__class__.__name__)
self._config = config
self._loss_dict = dict(gmsd=losses.GMSDLoss(),
l_inf_norm=losses.LInfNorm(),
laploss=losses.LaplacianPyramidLoss(),
logcosh=k_losses.logcosh,
ms_ssim=losses.MSSIMLoss(),
mae=k_losses.mean_absolute_error,
mse=k_losses.mean_squared_error,
pixel_gradient_diff=losses.GradientLoss(),
ssim=losses.DSSIMObjective(),
smooth_loss=losses.GeneralizedLoss(),)
self._mask_channels = self._get_mask_channels()
self._inputs: List[keras.layers.Layer] = []
self._names: List[str] = []
self._funcs: Dict[str, Callable] = {}
logger.debug("Initialized: %s", self.__class__.__name__)
from keras import backend as K
from keras import losses as k_losses
from keras.layers import Conv2D
from keras.models import Sequential
from keras.optimizers import Adam
from lib.model import losses
from lib.utils import get_backend
_PARAMS = [
(losses.GeneralizedLoss(), (2, 16, 16)),
(losses.GradientLoss(), (2, 16, 16)),
# TODO Make sure these output dimensions are correct
(losses.GMSDLoss(), (2, 1, 1)),
# TODO Make sure these output dimensions are correct
(losses.LInfNorm(), (2, 1, 1))
]
_IDS = ["GeneralizedLoss", "GradientLoss", "GMSDLoss", "LInfNorm"]
_IDS = ["{}[{}]".format(loss, get_backend().upper()) for loss in _IDS]
@pytest.mark.parametrize(["loss_func", "output_shape"], _PARAMS, ids=_IDS)
def test_loss_output(loss_func, output_shape):
""" Basic shape tests for loss functions. """
if get_backend() == "amd" and isinstance(loss_func, losses.GMSDLoss):
pytest.skip("GMSD Loss is not currently compatible with PlaidML")
y_a = K.variable(np.random.random((2, 16, 16, 3)))
y_b = K.variable(np.random.random((2, 16, 16, 3)))
objective_output = loss_func(y_a, y_b)
if get_backend() == "amd":
assert K.eval(objective_output).shape == output_shape
from lib.model import losses
from lib.utils import get_backend
if get_backend() == "amd":
from keras import backend as K, losses as k_losses
else:
# Ignore linting errors from Tensorflow's thoroughly broken import system
from tensorflow.keras import backend as K, losses as k_losses # pylint:disable=import-error
_PARAMS = [(losses.GeneralizedLoss(), (2, 16, 16)),
(losses.GradientLoss(), (2, 16, 16)),
# TODO Make sure these output dimensions are correct
(losses.GMSDLoss(), (2, 1, 1)),
# TODO Make sure these output dimensions are correct
(losses.LInfNorm(), (2, 1, 1))]
_IDS = ["GeneralizedLoss", "GradientLoss", "GMSDLoss", "LInfNorm"]
_IDS = [f"{loss}[{get_backend().upper()}]" for loss in _IDS]
@pytest.mark.parametrize(["loss_func", "output_shape"], _PARAMS, ids=_IDS)
def test_loss_output(loss_func, output_shape):
""" Basic shape tests for loss functions. """
if get_backend() == "amd" and isinstance(loss_func, losses.GMSDLoss):
pytest.skip("GMSD Loss is not currently compatible with PlaidML")
y_a = K.variable(np.random.random((2, 16, 16, 3)))
y_b = K.variable(np.random.random((2, 16, 16, 3)))
objective_output = loss_func(y_a, y_b)
if get_backend() == "amd":
assert K.eval(objective_output).shape == output_shape
else:
from keras import backend as K
from keras import losses as k_losses
from keras.layers import Conv2D
from keras.models import Sequential
from keras.optimizers import Adam
from lib.model import losses
from lib.utils import get_backend
_PARAMS = [
(losses.GeneralizedLoss(), (2, 16, 16)),
(losses.GradientLoss(), (2, 16, 16)),
# TODO Make sure these output dimensions are correct
(losses.GMSDLoss(), (2, 1, 1)),
# TODO Make sure these output dimensions are correct
(losses.LInfNorm(), (2, 1, 1))
]
_IDS = ["GeneralizedLoss", "GradientLoss", "GMSDLoss", "LInfNorm"]
_IDS = ["{}[{}]".format(loss, get_backend().upper()) for loss in _IDS]
@pytest.mark.parametrize(["loss_func", "output_shape"], _PARAMS, ids=_IDS)
def test_loss_output(loss_func, output_shape):
""" Basic shape tests for loss functions. """
if get_backend() == "amd" and isinstance(loss_func, losses.GMSDLoss):
pytest.skip("GMSD Loss is not currently compatible with PlaidML")
y_a = K.variable(np.random.random((2, 16, 16, 3)))
y_b = K.variable(np.random.random((2, 16, 16, 3)))
objective_output = loss_func(y_a, y_b)
if get_backend() == "amd":
assert K.eval(objective_output).shape == output_shape