jnulzl

直接用pytorch加载，不用解压的

i want to know if both stages share parameters in the same layer?

@frankxyy @muyi6 ref [Making dynamic input shapes fixed](https://onnxruntime.ai/docs/tutorials/mobile/helpers/make-dynamic-shape-fixed.html)

@jvivo https://github.com/aadhithya/onnx-typecast

@qnmts ```python python scripts/export_onnx_model.py --checkpoint weights/mobile_sam.pt --model-type vit_t --opset 11 --output mobile_sam_onnx_opset11.onnx ``` 

@qnmts I didn't meet your error. You can try to update your code to the latest and try again.

@zhouhao-learning OTC-MMFD-11846496

@linshilun 改自VGG

met same problems too!