Complete code for training with zero annotations (Issue #43) #221
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Outdated suggestions cannot be applied.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.
Hi,
I have incorporated NiklasWilson code and also corrected utils.py in order to be able to be able to use the lines with no bounding boxes in data_train.txt.
There was a message "Ignoreable error: Folder/File could not be accessed, may not exist ->" that I thought could mislead the user so I improved it to say "Sometimes it is desirable that your training dataset include images with non-labeled objects that you do not want to detect (i.e. negative samples without bounding box). Non-annotated images can be placed in -> /home/username/Src/TrainYourOwnYOLO/Data/Source_Images/no_object. However, this is not mandatory, you can now continue with the training."
I think that it is complete and ready to use. Feel free to merge into the master if you like.