[WIP] 90 dense vnet

[dwml]

Fixes #90

Description

A few sentences describing the changes proposed in this pull request.

Status

Work in progress

Types of changes

• Non-breaking change (fix or new feature that would not break existing functionality).
• Breaking change (fix or new feature that would cause existing functionality to change).
• New tests added to cover the changes.
• Integration tests passed locally by running ./runtests.sh -f -u --net --coverage.
• Quick tests passed locally by running ./runtests.sh --quick --unittests --disttests.
• In-line docstrings updated.
• Documentation updated, tested make html command in the docs/ folder.

[dwml]

In the dense vnet a channel sparse convolutional layer is used. In niftynet this was implemented here: https://niftynet.readthedocs.io/en/dev/_modules/niftynet/layer/channel_sparse_convolution.html#ChannelSparseConvLayer
Does anyone know if there is an implementation of this in MONAI?

[wyli]

In the dense vnet a channel sparse convolutional layer is used. In niftynet this was implemented here: https://niftynet.readthedocs.io/en/dev/_modules/niftynet/layer/channel_sparse_convolution.html#ChannelSparseConvLayer Does anyone know if there is an implementation of this in MONAI?

it's not implemented yet, perhaps we can have a non-dropout version first, then bring in that in later PRs?

[carlpe]

Any chance to update this?