Performance may be reduced when using .pb and .tflite tensorflow model

[peace195]

I need helps to review the YOLOv3 tensorflow version: https://github.com/peace195/tensorflow-lite-yolo-v3/blob/master/yolo_v3.py

It is the cause of reducing performance when using .pb and .tflite compare with darknet .weights.

[peace195]

Please test the performance and give me your feedback.

[nscotto]

Thanks! Will do feedback as soon as I can.

[titanbender]

I've tested the models before and after conversion and I'm seeing significant worse results with the tf lite model. I'm wondering if the parameters are not configured correct.

[peace195]

@titanbender Thanks. Let me investigate and fix it 👍

[balajib363]

@titanbender I converted yolov3 tiny model to tflite but I am doing something wrong when i build in android app using tensorflow. Could guide with steps tobe followed before building in mobile app??
Thanks

[franck-armand]

After getting the .pb file, do you necessarily need to set the Docker env to get the .tflite ? also how should I set it? I am not quite familiar with how it works. thanks