Allow folders for the train and validation paths. #168
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
This changes in the `taming/data/custom.py` file allow the use of folders for the training and validation paths while been compatible with how it was used before. This should make it easier to train on custom data as you no longer need to create a `train.txt` and `val.txt` file manually which sometimes can be a time-consuming and tedious task, now you can just create two folders, one for the train and one for the validation containing the images inside and the script will discover the files and create the list of paths by itself, this can also allow you to add more images to those folders later without having to manually recreate the train and validation files, not sure about the use for that but the option is there.
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Outdated suggestions cannot be applied.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.
This changes in the
taming/data/custom.pyfile allow the use of folders for the training and validation paths while been compatible with how it was used before. This should make it easier to train on custom data as you no longer need to create atrain.txtandval.txtfile manually which sometimes can be a time-consuming and tedious task, now you can just create two folders, one for the train and one for the validation containing the images inside and the script will discover the files and create the list of paths by itself, this can also allow you to add more images to those folders later without having to manually recreate the train and validation files, not sure about the use for that but the option is there.