search

xinghaochen / TinySAM

Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"
Apache License 2.0
403 stars 23 forks source link

Why is the mask a three-channel image? How do I export Onnx files? #10

Closed duxuan11 closed 10 months ago

duxuan11 commented 10 months ago

I don't know what you changed about the original SAM, but when mask is used as output, it has three channels instead of one. And use max score to select.

shuh15 commented 10 months ago

yes, we adopt multi-output mode to train the network, which means the number of output masks is 3, among which we select the one with max score as the final output mask. As for exporting onnx files, samexporter would be helpful.