Format bboxes - exporting tflite graphs

[EstelaVMonjardin]

If I am not mistaken this docstring (

models/research/object_detection/export_tflite_graph_lib_tf2.py

Line 160 in 9c8cbd0

Args:

) is not correct, the image input would not be a float32 tensor of shape [num_anchors, 4] containing the anchor boxes but a float32 tensor of shape model_input_size containing the image we are doing inference over.

Moreover, I would like to know the format of the output boxes, which coordinates are used in this case?

Thank you for reading.