onnx2keras | Convert ONNX model graph to Keras model format | Machine Learning library

I have a python script that takes an ONNX Neural Network and converts it to a keras (.h5) model to be trained and exported back into ONNX as a newly trained model to be deployed later. The problem is that I am required to create a python .exe file from the python script as the goal is to deploy the deep learning model in C Plus Plus. Currently, the Python script does a great job of altering the onnx program for the C Plus Plus program to deploy the trained model, and successfully creates a .exe file with Pyinstaller with the following command:

My question:

A straightforward experiment that I conducted showed that using padding='SAME' in a conv2d layer in Keras/TF is different from using padding='VALID' with a preceding zero-padding layer.

1. How is that possible?
2. Does Keras/TF pads zeros symmetrically around the tensor?

Explanation of the experiment - just if you're interested in reading further:

I used the onnx2keras package to convert my Pytorch model into keras/TF.

When onnx2keras encounters a convolutional layer with padding > 0 in the ONNX model, it translates it to Keras' Conv2D with valid padding (i.e., no padding!), preceded by Keras' ZeroPadding2D layer. This works very well and returns outputs that are identical to those produced by the Pytorch network.

I yet thought it was strange that it didn't simply used padding='SAME', as most of the references say that Keras/TF use zero padding, just like Pytorch does.

Nevertheless, I patched onnx2keras and made it produce me Conv2D layers with padding='SAME' rather than the existing solution of 'VALID' padding with a preceding zero-padding layer. This made the resulting model return different outputs than the one with the zero-padding layer, and of course different from my Pytorch model, which was identical until the patch.