Please add notes about converting .pb mobilenet to .tflite format #7
Description
Hello!
I am developing a mobile application for grocery detection. Currently I have stuck on custom object detection training at mobilenet convertion to tflite format.
I have raised an issue at offical TensorFlow repo, but unfortunately there is no answer. Thread: tensorflow/models#8786.
All results I got were raising exepction on load by Flutters tflite module.
Suprisingly mobilenet mentioned in Yours repos README (https://drive.google.com/file/d/1Ha9yfjkweCatEo6UoZgZyHMeyIBGe5FO/view) is loaded properly and correctly detects objects on recordings.
This feature is crucial for application, to be useful.
I would be grateful if You could share some knowledge about:
- how to convert .pd SSD MobileNet to THIS (https://drive.google.com/file/d/1Ha9yfjkweCatEo6UoZgZyHMeyIBGe5FO/view) format (scripts and details like Python and TensorFlow version)
Example scenario:
- Download SSD MobileNet from tfs' offical repo (https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md) for example: ssd_mobilenet_v2_quantized_coco
- Convert it to .tflite format
- SSD MobileNet is loaded with success by flutter and correctly detects objects
I have followed several tutorials, but it seems like they are not a solution.
I would be pleased for an answer