basic dataset #5
Closed
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
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
It looks like what we'd need to do is convert the dictconf into the dataclasses using https://omegaconf.readthedocs.io/en/latest/usage.html#omegaconf-to-object ? |
humanpose1
reviewed
Jul 21, 2021
| - task: ??? | ||
| - models: ??? | ||
| - data: ??? | ||
| defaults: # loads default configs |
There was a problem hiding this comment.
Ok for now. Maybe in the future, we will change this to have multiple optimizers.
There was a problem hiding this comment.
I agree, eventually we should change the optimizer to be part of the model package.
|
Btw I got this error: |
humanpose1
reviewed
Jul 21, 2021
for more information, see https://pre-commit.ci
|
That's strange about the error, can you send a stack trace? |
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Outdated suggestions cannot be applied.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.
@humanpose1 let me know what you think... it's very crude but it at least runs.
Right now it will instantiate the s3dis1x1 dataset.
You can try running it with
python train.py model=default dataset=segmentation/s3dis/s3dis1x1.yamlI think the first thing we should figure out is how to properly implement static typechecking for the configs (#4) or just abandon the
DataConfig. It looks like pytorch lightning transformers implemented the dataconfig but didn't actually make it do any type checking...