![]() ![]() We expect the path to the saved_model directory. You find an end-to-end tutorial for ssd-mobilenet here CLI reference If you have the option of going to your model provider and obtaining the model in saved model format, then we recommend doing so. The summarize_graph tool does need to be downloaded and built from source. If your model is in checkpoint or graphdef format and you do not know the input and output nodes of the model, you can use the summarize_graph TensorFlow utility. Python -m nvert -graphdef tensorflow-model-graphdef-file -output model.onnx -inputs input0:0,input1:0 -outputs output0:0 Python -m nvert -checkpoint tensorflow-model-meta-file-path -output model.onnx -inputs input0:0,input1:0 -outputs output0:0 If your TensorFlow model is in a format other than saved model, then you need to provide the inputs and outputs of the model graph. Python -m nvert -saved-model tensorflow-model-path -opset 10 -output model.onnx If you are unsure about which opset to use, refer to the ONNX operator documentation. ![]() If you need a newer opset, or want to limit your model to use an older opset then you can provide the -opset argument to the command. ![]() The above command uses a default of 8 for the ONNX opset. Python -m nvert -saved-model tensorflow-model-path -output model.onnx
0 Comments
Leave a Reply. |