composer.models#
The models module contains the ComposerModel
base class along with reference
implementations of many common models. Additionally, it includes task-specific convenience
ComposerModel
s that wrap existing Pytorch models with standard forward passes
and logging to enable quick interaction with the Trainer
.
See Composer Model for more details.
Functions
Helper function to create a |
|
Helper function to create a |
|
Helper function to create a |
|
Helper function to create a |
|
A wrapper around timm.create_model() used to create |
|
BERT classification model based on ๐ค Transformers. |
|
BERT model based on ๐ค Transformers. |
|
Implements |
|
Helper function to create a |
|
Helper function to create a |
Classes
A convenience class that creates a |
|
A wrapper class that converts ๐ค Transformers models to composer models. |
|
Sets the initialization scheme for different layers of a PyTorch model. |
|
Single Shot Object detection Model with pretrained ResNet34 backbone extending |
|
A U-Net model extending |
Hparams
These classes are used with yahp
for YAML
-based configuration.
YAHP interface for |
|
YAHP interface for |
|
YAHP interface for |
|
YAHP interface for |
|
YAHP interface for |
|
YAHP interface for |
|
General YAHP interface for ComposerModels. |
|
|
|
YAHP interface for |
|
YAHP interface for |
|
YAHP interface for |