onnx-tensorflow
onnx-tensorflow copied to clipboard
How does onnx to tensorflow conversion happen ?
I was reading about the conversion of pytorch to onnx, the conversion happens because of a parser which takes the dummy input into the pytorch model and looks for the flow and generates a model with similar flow in onnx format.
I'm keen on knowing how onnx to tensorflow conversion happens at the backend, can anyone explain the same please ?
The onnx-tf converter takes an onnx model graph and converts node by node to a Tensorflow graph. The converted graph/model can be saved as a Tensorflow SavedModel and used for inference.