ONNX inference for MaskGenerator

mit-han-lab / efficientvit

EfficientViT is a new family of vision models for efficient high-resolution vision.

Apache License 2.0

1.79k stars 164 forks source link

ONNX inference for MaskGenerator #117

Open yujunsun110 opened 3 months ago

yujunsun110 commented 3 months ago

Hi,

I'm trying to do full image segmentation with an ONNX model. However, I observed that only the pytorch implementation is given for this task, while box and point prompts aided predictors are implemented. Is there a reason to avoid ONNX inference with mask generator?