add license plate model example #244
Merged
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
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Outdated suggestions cannot be applied.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.
In this PR, I'm adding an example for detecting license plates with YOLOv3. The model has obviously been trained with this Keras implementation. This also includes the configuration file in
zoo/.Apart from this change, I've also added some lines to limit the GPU usage down to a given percentage so as to not get the infamous
CUDA_OUT_OF_MEMORY. Also, I've setallow_growth = Trueto not allow the GPU to preallocate memory and to let it use just as much as it needs. See https://stackoverflow.com/a/39467358/2096747.I've added a
debug = Falsevariable intrain.pyto prevent getting too many debug messages while training - this has the benefit of being able to witness the model's progress (on the loss) as it trains.Added
create_validation_script.shscript to divide the dataset into training and validation sets (for VOC format).Added requirements file for the project to work. Without it, time is wasted finding out the right dependencies, especially with TensorFlow and Keras.