[AutoMM] Support customizing image data augmentation #3022
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
zhiqiangdon
added
the
model list checked
| ]: | ||
| if not all([isinstance(trans, str) for trans in hyperparameters[k]]): | ||
| advanced_hyperparameters[k] = copy.deepcopy(v) | ||
| hyperparameters[k] = [] |
There was a problem hiding this comment.
After split, the hyperparameter dict itself doesn't aware whether it has been splitted or not. Basically, some advanced hyperparameters are modified (not deleted), and copied to another variable, where the naive hyperparameters don't have access to.
Since hyperparameter space has been divided into subspaces with the dot delimitor, how about moving advanced hyperparameters into 'advanced.xxx' subspace ?? Potentially, with OmegaConf, we can easily access to these advanced hyperparameters with config.advanced.
There was a problem hiding this comment.
Here we split out model.timm_image.train_transforms and model.timm_image.val_transforms when their values are lists of callable objects instead of lists of strings. OmegConf is designed to store simple config values, e.g., number or string. Adding config.advanced still can't handle the hyperprameters with callable objects.
|
Job PR-3022-b27d45a is done. |
|
Job PR-3022-a437272 is done. |
|
Job PR-3022-aad3473 is done. |
Issue #, if available:
Description of changes:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.