0

The last layer it has is a layer whose output is a 13x13x75 matrix, when it should be 1x10 since 10 is the number of output classes.

It lacks layers, including the layer logits. When you download the model it comes with some python files to use it and in these files you see all the processing that must be done to get to a 1x10 matrix.

The point is that this code should not exist and everything must be within the model.

What is the file with the .pb extension?

Does anyone know what could be happening?

cthrash
  • 2,938
  • 2
  • 11
  • 10
Diego Aguirre
  • 11
  • 1

1 Answers1

1

Sorry about the confusion.

What is the file with the .pb extension? That is the TensorFlow model you load to do inferencing.

Guessing from the 13 x 13 x 75 output you received you created a Object-Detection model(OD) but you were expecting a 1 x 10 output indicating to me that you want a multi-label model.

Multi-Label: Returns the 1x10 vector you are expecting.

OD: Is meant to provide bounding box info as well as confidence; it requires custom code to compute that is not supported in the pipeline; that is why the final processing needs to be done in the python code ('object_detection.py').

kurt,

kurt
  • 11
  • 2