sct_deepseg_gm: Removed restriction on the network input size (small inputs): Fixes bug that appeared when inputting images with small FOV #1877
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Outdated suggestions cannot be applied.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.
I just realized that given that I can dynamically change the TensorFlow model input size for that particular model architecture that I'm using, it makes it possible to handle input sizes smaller than the sizes that the network was trained on by avoiding padding.
This PR removes the restriction error that we had for smaller volume sizes (after resampling), that was usually thrown when the user inputs a cropped volume. That shouldn't be an issue anymore because now the network input size is dynamically resized (a property of the ASPP architecture allow that). For larger sizes, the process continues the same, with the traditional cropping.