Pix2PixLoss¶
Inheritance Diagram
-
class
ashpy.losses.gan.
Pix2PixLoss
(l1_loss_weight=100.0, adversarial_loss_weight=1.0, feature_matching_weight=10.0, adversarial_loss_type=<AdversarialLossType.GAN: 1>, use_feature_matching_loss=False)[source]¶ Bases:
ashpy.losses.executor.SumExecutor
Pix2Pix Loss.
Weighted sum of
ashpy.losses.gan.GeneratorL1
,ashpy.losses.gan.AdversarialLossG
andashpy.losses.gan.FeatureMatchingLoss
.Used by Pix2Pix [1] and Pix2PixHD [2]
- 1
Image-to-Image Translation with Conditional Adversarial Networks https://arxiv.org/abs/1611.07004
- 2
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs https://arxiv.org/abs/1711.11585
Methods
__init__
([l1_loss_weight, …])Initialize the loss.
Attributes
executors
Return the List of Executors.
fn
Return the Keras loss function to execute.
global_batch_size
Global batch size comprises the batch size for each cpu.
weight
Return the loss weight.
-
__init__
(l1_loss_weight=100.0, adversarial_loss_weight=1.0, feature_matching_weight=10.0, adversarial_loss_type=<AdversarialLossType.GAN: 1>, use_feature_matching_loss=False)[source]¶ Initialize the loss.
Weighted sum of
ashpy.losses.gan.GeneratorL1
,ashpy.losses.gan.AdversarialLossG
andashpy.losses.gan.FeatureMatchingLoss
.- Parameters
l1_loss_weight (
ashpy.ashtypes.TWeight
) – Weight of L1 loss.adversarial_loss_weight (
ashpy.ashtypes.TWeight
) – Weight of adversarial loss.feature_matching_weight (
ashpy.ashtypes.TWeight
) – Weight of the feature matching loss.adversarial_loss_type (
ashpy.losses.gan.AdversarialLossType
) – Adversarial loss type (ashpy.losses.gan.AdversarialLossType.GAN
orashpy.losses.gan.AdversarialLossType.LSGAN
).use_feature_matching_loss (bool) – if True use also uses
ashpy.losses.gan.FeatureMatchingLoss
.
- Return type