Mathieu Poumeyrol
Mathieu Poumeyrol
Hello, thanks for your interest in tract! M1 chips are weird beasts, so your mileage may vary. I am doing some work on the side at this current stage to...
Quick assessment on perf for the model, no obvious performance sink. On a linux box: ``` NUC 01/02 9:35 ~/dev/sonos/tract/issue-955% tract yolov5s.onnx -O dump --cost --profile --allow-random-input [...] Most time...
1.5s/i feels high. I'll try and have a look on a pi4.
Hello ! thanks for your interest in tract. First, let's clarify a couple of things, just in case. * during analysis and model preparations, symbols in tract are "universal" not...
About the dots in symbol... do you know how this model was generated ? I'm trying to guess if dots in symbols is an idiosyncrasy of this particular models for...
Allowed the dots and added the floor function in #1823., just basically like you did. I also rewrote the recursing bit of the parser so it is less likely to...
With the previous patches in places on tract main, the above model now fails like this. It looks like tract computed the output shape (from inputs ?) but it does...
Answer to 1 is, from the ONNX file ! A couple of things hints that the model comes from https://www.paddleocr.ai/main/en/version2.x/legacy/paddle2onnx.html . So this ONNX converter apparently includes symbolic shape information...
Ha, thanks, a dump of the graphs with the shapes would be ideal.
this should be helpful indeed. stay tuned.