Description

This PR build fully convolutional models based on any compatible torchvision model and convert the adaptive average pooling layer to a 7x7 average pooling. This model allows for using pre-trained torchvision models with any number of output classes, and most importantly enable a much faster inference in use cases like pathology where the input images are huge.

Status

Ready

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.
• In-line docstrings updated.
• [x ] Documentation updated, tested make html command in the docs/ folder.