Post-training integer quantization for SSDMobileNet - poor detection accuracy

Hi there

Describe the bug
I used Convert TF Object Detection API model to TFLite and tried to modify it, so it is fully int 8 quantized. Here is my version. It should completely run on its own in Colab.

In the notebook I use two different functions to create the different representative datasets. The first one uses 200 images from the coco dataset, the second one only 2. However, the resulting models seem to perform quite similarly poorly. Therefore I guess I did something wrong but can't find the mistake.

You can see the results of the models at the very end of the colab but I also will add some Screenshots.

System information

I didn't change the standard Installation on google Colab.

Python version:

Describe the expected behavior

The first generated tflite model should perform much better than the second and detect all easy cases.

Describe the current behavior
They both perform bad.

Code to reproduce the issue
Here is my version. It should completely run on its own on Colab.

Screenshots

Model 2 outperforms Model 1

Result Model 1

Result Model 2

Both perform okay

Result Model 1

Result Model 2

Both perform poorly

Result Model 1 & 2

Additional context
If you have any questions about my code don't hesitate to ask! Thank you very much.

Start by running the linked Colab notebook and compare the two representative-dataset paths used to produce the fully int8 TFLite SSDMobileNet models. Check the final model results against the reported screenshots; done means identifying and correcting the quantization workflow so the model using 200 COCO images performs as expected and the notebook remains reproducible in Colab.