composer.models.deeplabv3.deeplabv3_hparams#
composer.models.deeplabv3.deeplabv3_hparams
Functions
Returns the same class as was passed in, with dunder methods added based on the fields defined in the class. |
Hparams
These classes are used with yahp
for YAML
-based configuration.
This class specifies arguments for a DeepLabV3 model and can instantiate a DeepLabV3 model. |
|
Model Hparams. |
- class composer.models.deeplabv3.deeplabv3_hparams.DeepLabV3Hparams(initializers=<factory>, num_classes=None, backbone_arch='resnet101', is_backbone_pretrained=True, sync_bn=True)[source]#
Bases:
composer.models.model_hparams.ModelHparams
This class specifies arguments for a DeepLabV3 model and can instantiate a DeepLabV3 model.
- Parameters
backbone_arch (str) โ the backbone architecture to use, either [โresnet50โ, โresnet101โ]. Default is โresnet101โ.
is_backbone_pretrained (bool) โ if true (default), use pre-trained weights for backbone.
sync_bn (bool) โ if true (default), use SyncBatchNorm to sync batch norm statistics across GPUs.