问题
I am trying to use tf-serving to deploy my torch model. I have exported my torch model to onnx. How could I generate the pb model for tf-serving ?
回答1:
Use the onnx/onnx-tensorflow converter tool as a Tensorflow backend for ONNX.
Install onnx-tensorflow:
pip install onnx-tf
Convert using the command line tool:
onnx-tf convert -t tf -i /path/to/input.onnx -o /path/to/output.pb
Alternatively, you can convert through the python API.
import onnx
from onnx_tf.backend import prepare
onnx_model = onnx.load("input_path") # load onnx model
tf_rep = prepare(onnx_model) # prepare tf representation
tf_rep.export_graph("output_path") # export the model
来源:https://stackoverflow.com/questions/58834684/how-could-i-convert-onnx-model-to-tensorflow-saved-model