Simplify PyTorch interact feature computation#186
Simplify PyTorch interact feature computation#186yocox wants to merge 1 commit intofacebookresearch:mainfrom
Conversation
The original implementation use torch.cat() & view() (a.k.a reshape) to combine feature vectors into a matrix. It create a Reshape operation in the exported ONNX, and create dynamic tesnor. It can be replace by just one torch.stack(). The result graph is simpler and faster.
|
Hi @yocox! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@fb.com. Thanks! |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Facebook open source project. Thanks! |
facebook-github-bot
added
the
CLA Signed
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Facebook open source project. Thanks! |
2 similar comments
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Facebook open source project. Thanks! |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Facebook open source project. Thanks! |
3 participants
The original implementation use
torch.cat()&view()(a.k.a reshape)to combine feature vectors into a matrix. It create a
Reshapeoperationin the exported ONNX, and create dynamic tensor.
It can be replace by just one
torch.stack(). The result graph issimpler and faster.