Mathieu Poumeyrol
Mathieu Poumeyrol
I guess this is another nice little mess. Can we take a step back ? What is it you are trying to achieve ?
Lol. Well, the cli has grown organically to meet what I needed to make tract-the-library development easier. So yeah, no surprise it's not consistent. Being consistent betweean ONNX/TF and NNEF...
@tgolsson I think #771 may address most of these concerns. It moves shape overrides very earlier on, changing the nnef AST before we build the model. Tell me what you...
Are we happy with the current solution ? Should we close this one ?
mmm... maybe try `--input-node input -i 1,3,...` ?
The assert is overzealous. We need to distinguish the two kind of Source: "external" is a strict nnef-compatible source, while "tract_core_external" adds support for symbolic dimensions. So the assert should...
All right, thanks for giving it a shot, I guess I'll take a look. Is this model one you've already shared with me ?
OK... Not sure I chose the right way to fix. Trying to recap here. Our model NNEF starts with these lines: ``` graph network( input ) -> ( output )...
I think I get it to work (there was a hard-to-track bug in Concat...) This new global --set is performed right after decluttering. So ```cargo run --bin tract -- image.nnef.tar...
Did you really send me this model ? :)