TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10
TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10 copied to clipboard
Train using images instead of tfrecord?
I am working with a huge dataset and RAM is my limitation as it gets full during creation of tfrecords. Is it possible to do this training using images and labels directly instead of first creating and then using tfrecords?