This repository has been archived by the owner on Mar 21, 2024. It is now read-only.
Added possibility to set num_downsampling_paths for Unet as part of model configuration #425
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The
Unet
parameternum_downsampling_paths
defines the number of network layers. It was previously always set to4
, but can now be modified as a part of model configuration. The default value remains4
. A lower value may be useful for decreasing memory requirements, of for working with shorter images. (The minimum number of image slices required when using a network ofn
layers is2**n
.)The parameter
num-downsampling-paths
is initialised in InnerEye/ML/config.py, then is used inUnet
creation in thebuild_net()
function of InnerEye/ML/utils/model_util.py. An associated unit test has been added to Tests/ML/test_config_helpers.py.