I would like to fine-tune a pretrained efficientdet-lite0 model on my dataset and then do post training quantization (full int8). What is the recommended way of doing this? I did not find any documentation on this in the repository, however since efficientdet-lite was designed to be resistant to quantization I wonder how to do this.
I would like to fine-tune a pretrained efficientdet-lite0 model on my dataset and then do post training quantization (full int8). What is the recommended way of doing this? I did not find any documentation on this in the repository, however since efficientdet-lite was designed to be resistant to quantization I wonder how to do this.