deeplabv3_hparams#
YAHP interface for composer_deeplabv3()
.
Hparams
These classes are used with yahp
for YAML
-based configuration.
YAHP interface for |
- class composer.models.deeplabv3.deeplabv3_hparams.DeepLabV3Hparams(initializers=<factory>, num_classes=None, backbone_arch='resnet101', backbone_weights=None, use_plus=True, sync_bn=True, ignore_index=-1, cross_entropy_weight=1.0, dice_weight=0.0)[source]#
Bases:
composer.models.model_hparams.ModelHparams
- YAHP interface for
- Parameters
num_classes (int) โ Number of classes in the segmentation task.
backbone_arch (str, optional) โ The architecture to use for the backbone. Must be either [
'resnet50'
,'resnet101'
]. Default:'resnet101'
.backbone_weights (str, optional) โ If specified, the PyTorch pre-trained weights to load for the backbone. Currently, only [โIMAGENET1K_V1โ, โIMAGENET1K_V2โ] are supported. Default:
None
.use_plus (bool, optional) โ If
True
, use DeepLabv3+ head instead of DeepLabv3. Default:True
.sync_bn (bool, optional) โ If
True
, replace all BatchNorm layers with SyncBatchNorm layers. Default:True
.initializers (List[Initializer], optional) โ Initializers for the model.
[]
for no initialization. Default:[]
.