We're trying to train a bib detector here.
data_rawis just the place where the images are downloaded and wait to be annotated.
datahas annotated data.
data/bib_detection/annotationshas a collection of images in the format given by VGG Image Annotator. These images are ready to be processed by
create_tf_records.pyto build the TF examples.
data/number_recognition/annotationscontains images of bibs. Some of the images were cropped using the data from ground truth for bib detection and others were cropped using the predictions of the bib detector. All annotations are kept in a single file
modelscontains code from
https://github.com/tensorflow/models. More specifically, it contains the
Training the bib detector
The images are grouped in directories by event. Each directory contains a few
images and one
.csv file which contains the annotations.
This structure needs to be kept strictly or the
won't work correctly.
How to start training
- If required on your environment, activate Tensor Flow:
- Set up the model:
- Start the training job:
- Start the evaluation job:
Training the number recognizer