Jonas Christophersen

GPU memory requirements increases when using DCNv3_pytorch rather than DCNv3

2

Thank you for this awesome implementation! I've been using the InternImage as a backbone of my Detectron2 Faster-R-CNN implementation. My trained models need to run on CPU, so I tried...

Thank you for this awesome implementation! I've been using the InternImage as a backbone of my Detectron2 Faster-R-CNN implementation. My trained models need to run on CPU, so I tried...

I've been experimenting with converting my model to ONNX format, however while I am able to get the model exported and run with identical outputs between torchscript and ONNX, the...