Use hydra for instantiating models and optimizers #295
Conversation
This file contains 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
remtav
commented
Mar 22, 2022
| # '\nThe NIR modality will be fed at first layer of model alongside other bands,' | ||
| # '\nthe implementation of concatenation point at an intermediary layer is only available' | ||
| # '\nfor the deeplabv3 model for now. \nMore will follow on demand.' | ||
| # ) |
There was a problem hiding this comment.
This warning is broken since we wouldn't use cfg.model.model_name anymore. It's an easy fix, but not sure this warning is necessary. Our smp models can read NIR and recycle other bands' weights. Maybe some documentation could be added to our deeplav3 dualhead and that would be enough. @CharlesAuthier ?
There was a problem hiding this comment.
yeaah its ok with me
There was a problem hiding this comment.
Ok! I'll remove this in PR #297
remtav
commented
Mar 22, 2022
| raise logging.critical(ValueError(f'\nThe model name {model_name} in the config.yaml is not defined.')) | ||
|
|
||
| return model | ||
| return instantiate(net_params, in_channels=in_channels, classes=out_classes) |
There was a problem hiding this comment.
Some hydra magic to rule out all if/else statements. wouhou!
CharlesAuthier
approved these changes
Mar 23, 2022
| # '\nThe NIR modality will be fed at first layer of model alongside other bands,' | ||
| # '\nthe implementation of concatenation point at an intermediary layer is only available' | ||
| # '\nfor the deeplabv3 model for now. \nMore will follow on demand.' | ||
| # ) |
There was a problem hiding this comment.
yeaah its ok with me
mpelchat04
approved these changes
Mar 23, 2022
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.
fixes #246 and #293 (breaking our one issue / one PR rule, forgive me!)
add tests for optimizer instantiation in test_optimizers.py
adapt our unet models (models/unet.py) to expect same parameter names as smp models