I'm currently working on training a RetinaNet model using TensorFlow and the Keras implementation provided in the official documentation (https://keras.io/examples/vision/retinanet/).However, I'm having difficulty understanding how to create a custom dataset using my image data and corresponding XML annotations.
I have tried with https://www.tensorflow.org/datasets/add_dataset but not able to understand. I would greatly appreciate it if someone could guide me through the process of creating a custom dataset in TensorFlow that can be used with the RetinaNet model. Specifically, I'm interested in how to parse the XML annotations, load the corresponding images, and prepare the data in a format that can be fed into the model during training.
Any explanations, code snippets, or references to additional resources that can help me understand and implement this custom dataset creation process would be highly valuable. Thank you in advance!
