JXFOnestep
JXFOnestep
I just alter the --opts, like this parser.add_argument( "--opts", help="Modify config options using the command-line 'KEY VALUE' pairs", default=['MODEL.WEIGHTS', 'sparse_inst_r50_giam_aug_2b7d68.pth', 'INPUT.MIN_SIZE_TEST', '512'], nargs=argparse.REMAINDER, )
> @nindanaoto Hello, which eigen version is in your computer? My eigen version is 3.4.0, and I met a series of errors like this `/usr/include/eigen3/unsupported/Eigen/CXX11/src/util/EmulateArray.h:258:30: error: redeclared with 1 template...
Me too! Have you fix it?
Have you fix it?
> Hi, I met the same problem, are you fixed it? I met the same problem, have you solved it?
我的是1.7，我下个1.12试一下
我用 pcl::io::savePCDFile("result.pcd", *mpGlobalMap) 保存点云，就卡住了，保存的点云也打不开， [pcl::PCDReader::read] Number of points read (12394578) is different than expected (67020370) 想问下你们有没有碰到这个错误
libtorch跟你提供的一致，我单独写了一个libtorch测试案例就不会报错，一旦加到SLAM框架中就报错，不知道是什么原因
这个问题解决了，因为我推理的时候用了GPU，后来用CPU版就没有这个问题了，但是又有新的问题了， terminate called after throwing an instance of 'c10::Error' what(): isTuple() INTERNAL ASSERT FAILED at "/home/jxf/environment/libtorch-1.8.0+cpu/include/ATen/core/ivalue_inl.h":1097, please report a bug to PyTorch. Expected Tuple but got GenericList Exception raised from...