Version 0.2.3

Fixed CUDA out of memory issue when training on large datasets.

Version 0.2.2

Bug fixes

Torchfusion 0.2.1

Bug fixes

TorchFusion 0.2

New in 0.2

• Improved Trainer Framework
• Support for multiple Inputs and Outputs
• New utilities for loading images, one-hot encoding and more.
• New Gan Framework with multiple layers of abstraction and implementation of
  Hinge GANs, GANs with divergence loss, Wasserstein GANs and Relativistic GANs.
• New GAN Applications with support for spectral normalization, conditional batch normalization, self attention, projection gans and resnet generators and discriminators
• A wider range of Initializers
• Enhanced summary function that not only provides you details about number of parameters, layers, input and output sizes
  but also provides the number of Flops(Multiply-Adds) for every Linear and Convolution layer in your network.
  Now, you can know the exact computational cost of any CNN architecure with just a single function!!!
• Visdom and Tensorboard Support
• Live metrics and loss visualizations, with option to save them permanently
• Support for persisting logs permanently
• Easy to use callbacks

Note: This version of torchfusion is well tested and research-ready, the core framework is now complete, Future releases of TorchFusion will include more specialized functions that will cut across multiple domains of deep learning

TorchFusion 0.1.1

Pre-Release of TorchFusion. This wheel is provided for Python 3.x .

What's new:

Some Bug fixes

TorchFusion 0.1.0 - PRE-RELEASE

Pre-Release of TorchFusion. This wheel is provided for Python 3.x .

What's new:

• Comprehensive trainer Framework
  
• Highly detailed summary function
  
• Metrics and Visualization utilities
  
• Image loaders optimized for Inference
  
• GAN Trainer framework
  
• Implementation of DCGAN and Improved Wasserstein GAN
  
• Layers including Depthwise Convolutions, Flatten and Reshape