Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

3 data preprocessing #8

Merged
merged 13 commits into from
Oct 21, 2020
Merged

3 data preprocessing #8

merged 13 commits into from
Oct 21, 2020

Conversation

charleslpan
Copy link
Collaborator

No description provided.

dastratakos and others added 13 commits October 16, 2020 14:06
This commit includes a files to parse XML files. I am still working on
loading images using Python's PIL. There is also a model to visualize
the annotations by drawing bounding boxes around labeled images.
The boxes are in one of three colors:
    - green for wearing a mask
    - yellow for wearing a mask incorrectly
    - red for not wearing a mask
Use python run_pipeline.py --help to see options. Also commented out
pytorch code because it is too complicated for now and is causing
compile-time errors.
The new dataset is formed by taking each of the original images and
cropping out each face as specified by the annotations. To create this
new dataset, you must have the original dataset in ./archive/images and
./archive/annotations. Then, run python crop.py, and a new directory will be
created called ./archive/cropped_images. Furthermore, a file called
cropped_labels.csv will be created to store the new labels for the
images matching to their ids.
SimpleImage.py will make it so we can take a png file and convert it to an image array.
Ignores .idea
@charleslpan charleslpan merged commit 43e4ebd into master Oct 21, 2020
This was linked to issues Oct 21, 2020
This pull request was closed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Command Line Arguments Data augmentation Data preprocessing and cleaning
3 participants