Leheng Li
Leheng Li
Hi, is the problem solved?
Hi, could you release the remaining code for other datasets?
> > When I run test_fcos_onnx_model.py.I encounted this: > > ` from fcos_core import _C ImportError: /home/dut-616/FCOS-master/fcos_core/_C.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E` > > I am using pytorch 1.4.0 and torchvision 0.5.0.dev20200107...
> I update my GCC version to 8 and solved this problem.[ https://linuxize.com/post/how-to-install-gcc-compiler-on-ubuntu-18-04/ You save my time!
> It works for me. But still OOM for a single A6000 finetuning.
similar problem in wan vace. inference speed in sd.cpp is slower than the original pytorch.