keras-onnx | Convert tf.keras/Keras models to ONNX | Machine Learning library

I want to convert keras .h5 model into ONNX model. But my model is trained channel last and I want it channel first. I found that there is an argument in keras2onnx.convert_keras called channel_first_inputs but couldn't find any example on how to use it on their official site.

I am doing this step as a part of the process of converting my keras model into .engine model. Is there any other way to do so without the need to onnx intermediate step?.

Searching for the parameter name inside the keras2onnx code, I found the following usage

• In Here: channel_first_inputs=['input_1']
• In Here: channel_first_inputs=[model.input_names[0]]

I am writing a python script, which converts any deep learning models from popular frameworks (TensorFlow, Keras, PyTorch) to ONNX format. Currently I have used tf2onnx for tensorflow and keras2onnx for keras to ONNX conversion, and those work.

Now PyTorch has integrated ONNX support, so I can save ONNX models from PyTorch directly. But the problem is I will need input tensor shape for that model, in order to save it in ONNX format. As you already might have guessed, I am writing this script to convert unknown deep learning models.

Here is PyTorch's tutorial for ONNX conversion. There it's written:

Limitations¶ The ONNX exporter is a trace-based exporter, which means that it operates by executing your model once, and exporting the operators which were actually run during this run. This means that if your model is dynamic, e.g., changes behavior depending on input data, the export won’t be accurate.

Similarly, a trace is might be valid only for a specific input size (which is one reason why we require explicit inputs on tracing). Most of the operators export size-agnostic versions and should work on different batch sizes or input sizes. We recommend examining the model trace and making sure the traced operators look reasonable.

The code snippet I am using is this: