Automate/ skip Aug_Strength variable when resuming from previous pkl #220
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
changed torch and cuda version to make it runnable on google colab again
fixed cuda version for google colab
Fixes issues with Colab being updated to Python 3.10 and CUDA 11.8
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Outdated suggestions cannot be applied.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.
Derrick - (Sorry if this isn't in the right place, this is my first time submitting a PR... i asked about this feature on the Slack channel and you mentioned to start a PR).
I noticed when training multiple models for a number of weeks - retyping the aug_strength (from the log.txt) gets somewhat redundant. I ask to please automate this step. I'm not sure if this value is recorded in the pkl file itself or not. But whatever the value is , if one just wants to resume and keep training the model - it would be much more stremlined if you can just put in the pkl file path you want to resume from and start training.
Thank you so much for your help!
resume_from = 'content.pkl'
aug_strength = 1.374 (<<Skip this step, or automate)
train_count = 100
mirror_x = False
mirror_y = False