I am training a ssd_inception neural network using the Tensorflow Object Detection API. In the pipeline config file, there are preprocessor options to augment images during training. Is there any way to introduce probability of applying a given preprocessing? E.g 20% that the image will change contrast etc. If not, are there any plans to do so?
Probability parameters in Tensorflow Object Detection API image preprocessesing
204 views Asked by Miroslav Stola At
1
We don't have any current plan to do that. But feel free to send in a pull request. We are happy to review.
See https://github.com/tensorflow/models/blob/master/object_detection/builders/preprocessor_builder.py and https://github.com/tensorflow/models/blob/master/object_detection/core/preprocessor.py to get started.