Support fold onnx symbolic dimension

microsoft / nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

MIT License

959 stars 163 forks source link

Closed mzmssg closed 3 years ago

xysmlx commented 3 years ago

Good feature!

Could you also update models/pytorch2onnx/ort_run_frozen_each_layer.py?

mzmssg commented 3 years ago

Good feature!

Could you also update models/pytorch2onnx/ort_run_frozen_each_layer.py?

updated