Torch-nets

Latest version: v0.2.0

Safety actively analyzes 715032 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 4 of 4

0.0.1rc

Release notes

Main updates

* Restructure how layers are composed as part of a `torch.nn.module` - see [`Layer`](https://github.com/mvinyard/torch-nets/blob/layer-restructure/torch_nets/core/_layer.py)
* In turn, see how `Layer` objects are structured into `torch.nn.Sequential` blocks (i.e., [`TorchNet`])(https://github.com/mvinyard/torch-nets/blob/layer-restructure/torch_nets/_torch_net.py)
* Some general guidance on organization principles of torch.nn.module, torch.nn.Sequential, etc. taken from [Pytorch-how-and-when-to-use-Module-Sequential-ModuleList-and-ModuleDict](https://github.com/FrancescoSaverioZuppichini/Pytorch-how-and-when-to-use-Module-Sequential-ModuleList-and-ModuleDict)
* And of course - as perhaps obvious - updated the name from `torch-composer` to the more succinct, `torch-nets`

Some to-do's remaining before the final release:

1. Add documentation and example notebooks
2. Add encoder / decoder modules
3. Add tests

Some general considerations:
1. How might be best to interface this with `pytorch_lightning.LightningModule`?

Autogenerated release notes

What's Changed
* Layer restructure by mvinyard in https://github.com/mvinyard/torch-nets/pull/2


**Full Changelog**: https://github.com/mvinyard/torch-nets/compare/v0.0.4rc...v0.0.1rc

Page 4 of 4

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.