Better time series support in the model configuration #214
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…arn into favyen/20250708-gee-changes
Previously, if we have a layer that is an image time series (contains multiple sub-layers over time), then in the model config we would need to have one DataInput per timestep. This PR adds two options in DataInput, load_all_item_groups and load_all_layers. - load_all_item_groups: this adds all item groups under the specified layer as options of layers to load. - load_all_layers: this reads all of the layer options concatenated on channel axis instead of randomly picking one option to read. So tho two options can be combined to read image time series. They are still treated as tensors with time concatenated over channel axis (T*CxHxW).
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Improve time series support in the model configuration file.
Previously, if we have a layer that is an image time series (contains multiple sub-layers over time), then in the model config we would need to have one DataInput per timestep. This PR adds two options in DataInput, load_all_item_groups and load_all_layers.
So the two options can be combined to read image time series. They are still treated as tensors with time concatenated over channel axis (T*CxHxW).
Resolves #174. Depends on #200.