Can I run a Caffe Model to Google Coral Edge TPU, it is mentioned about Tensor flow Lite model but Can I run a Caffe Model too?

Question

I want to run a Caffe Model for a object Detection purpose, but in the documentation of the Google Coral, it is mentioned that to run in the edge TPU, we need to quantize the tensor flow model. But I have trained my model using Caffe, so now I don't what are the Caffe model requirements to run the model at the Google Coral Edge TPU.

import tensorflow as tf converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir) converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.representative_dataset = representative_dataset converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8] converter.inference_input_type = tf.int8 # or tf.uint8 converter.inference_output_type = tf.int8 # or tf.uint8 tflite_quant_model = converter.convert()

#this is for the Tensorflow model, what about the Caffe Model?