mpaillassa

Hello, I think there is a bug with the tensorflow max_pool_with_argmax op. When running the op with onnxruntime, I find that the op returns the pooled values twice instead of...

Linear sum assignment matching failure

1

This is a failure that should be very rare so it's not necessary to fix this right now but it can happen that the linear sum assignment matching _fails_ to...

I open this PR regarding the number of significant digits to use for each parameter #107. I just started with the `obscuration` that had too many digits that I reduced...