could support the C++ inference? Export to to onnx，and forward with tensorrt?

MasterBin-IIAU / Unicorn

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

MIT License

953 stars 87 forks source link

could support the C++ inference? Export to to onnx，and forward with tensorrt? #7

Open xinsuinizhuan opened 2 years ago

MasterBin-IIAU commented 2 years ago

@xinsuinizhuan sorry, for now, the codebase does not support the functions you mentioned. Unicorn uses some operations (such as Depth-wise convolution, Group Normalization, and Deformable Attention), which may be unfriendly to deployment.

QSLee-Net commented 2 years ago