89
edits
Changes
no edit summary
After that, it was also recreated and retrained with quantization-aware training of TF 1.15. In this way, a fully quantized model was obtained after conversion.
So, it in the end, three converted models were obtained: a regular 32 bit floating point one, an 8 bit half quantized (only the weights, not the activations) one, and a fully quantized one.
The following images show the graphs of the models before conversion (click to enlarge):
{| class="wikitable" style="margin: auto;"
|+
|-
|[[File:ML - Keras1.15 fruitsmodel.png|none|thumb|1000x1000px]]
{| class="wikitable" style="margin: auto;"
|+
|-
|[[File:ML - TFL float fruitsmodel.png|none|thumb|1000x1000px]]
