models#
Modules
The ComposerModel base interface. |
|
The BERT model family using Hugging Face Transformers. |
|
A simple example convolutional neural network which can be used to classify MNIST data. |
|
DeepLabV3 for image segmentation. |
|
The EfficientNet model family is a set of convolutional neural networks that can be used as the basis for a variety of vision tasks, but were initially designed for image classification. |
|
The GPT-2 model family is set of transformer-based networks for autoregressive language modeling at various scales. |
|
A wrapper class that converts ๐ค Transformers models to composer models |
|
Module Initializers. |
|
General YAHP interface for Base ComposerModels. |
|
The ResNet model family is a set of convolutional neural networks described in Deep Residual Learning for Image Recognition (He et al, 2015). |
|
A ResNet model family adapted for CIFAR10 image sizes. |
|
SSD300 for object detection on MSCOCO. |
|
Model tasks are ComposerModels with forward passes and logging built-in for many common deep learning tasks. |
|
A wrapper around timm.create_model() used to create |
|
The Unet architecture used in image segmentation. |
|
Helper function to create a |
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 |
|
The interface needed to make a PyTorch model compatible with |
|
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 |