imaginaire.evaluation.segmentation package¶
Submodules¶
imaginaire.evaluation.segmentation.celebamask_hq module¶
-
class
imaginaire.evaluation.segmentation.celebamask_hq.
Unet
(feature_scale=4, n_classes=19, is_deconv=True, in_channels=3, is_batchnorm=True, image_size=512, use_dont_care=False)[source]¶ Bases:
torch.nn.modules.module.Module
-
forward
(images, align_corners=True)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
training
= None¶
-
-
class
imaginaire.evaluation.segmentation.celebamask_hq.
unetConv2
(in_size, out_size, is_batchnorm)[source]¶ Bases:
torch.nn.modules.module.Module
-
forward
(inputs)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
training
= None¶
-
-
class
imaginaire.evaluation.segmentation.celebamask_hq.
unetUp
(in_size, out_size, is_deconv, is_batchnorm)[source]¶ Bases:
torch.nn.modules.module.Module
-
forward
(inputs1, inputs2)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
training
= None¶
-
imaginaire.evaluation.segmentation.cocostuff module¶
-
class
imaginaire.evaluation.segmentation.cocostuff.
DeepLabV2
(n_classes=182, image_size=512, use_dont_care=True)[source]¶ Bases:
torch.nn.modules.module.Module
-
forward
(images, align_corners=True)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
training
= None¶
-
imaginaire.evaluation.segmentation.common module¶
-
class
imaginaire.evaluation.segmentation.common.
SegmentationHistModel
(seg_network)[source]¶ Bases:
torch.nn.modules.module.Module
-
forward
(data, fake_images, align_corners=True)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
training
= None¶
-