LightGlue-ONNX End_to_End model

[chenscottus]

Hi,

It looks like it is worth to implement the end-to-end model:

FYI ... OroChippw/LightGlue-OnnxRunner#23
Recently LightGlue-ONNX released there fused model which improve the performance substantially(~2x faster in my test) and change the format of the output tensor, making the current code not functional
output_tensors[2] is now the shape of (matchnum, 2) and the pairs are already computed(so you don't need to compute them yourself)
output_tensors[3] is now the shape of (matchnum), which denotes the matching score of each match
The following simple hack should do the work:
code ...

Thanks,

-Scott

[AIDajiangtang]

Hi,

It looks like it is worth to implement the end-to-end model:

FYI ... OroChippw/LightGlue-OnnxRunner#23 Recently LightGlue-ONNX released there fused model which improve the performance substantially(~2x faster in my test) and change the format of the output tensor, making the current code not functional output_tensors[2] is now the shape of (matchnum, 2) and the pairs are already computed(so you don't need to compute them yourself) output_tensors[3] is now the shape of (matchnum), which denotes the matching score of each match The following simple hack should do the work: code ...

Thanks,

-Scott

thanks for your infomation,I will try it later