-
Notifications
You must be signed in to change notification settings - Fork 630
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
FCOS-master/fcos_core/_C.cpython-36m-x86_64-linux-gnu.so) #161
Comments
@codylcs The error message you posted here is incomplete. |
the question now is that: Process finished with exit code 1 |
when torchvisio is changed as version=1.1.0 ,the question happened again: |
I got the same question and I don't know what to do... error:
env:
|
I have solved this problem. torch 1.0.0 + torchvision 0.2.1 + cudatoolkit 9.0 / 10.0 before, I forget to use conda to install cudatoolkit, which is necessary to build My env:
|
when running fcos_demo.py ,questions happend as flowing:
piled with GPU support (nms at fcos_core/csrc/nms.h:22)
frame #0: std::function<std::string ()>::operator()() const + 0x11 (0x7f03c2ace441 in /home/cody/anaconda3/envs/FCOS/lib/python3.6/site-packages/torch/lib/libc10.so)
frame #1: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x2a (0x7f03c2acdd7a in /home/cody/anaconda3/envs/FCOS/lib/python3.6/site-packages/torch/lib/libc10.so)
frame #2: nms(at::Tensor const&, at::Tensor const&, float) + 0xd4 (0x7f03beaff524 in /home/cody/PycharmProjects/FCOS/FCOS-master/fcos_core/_C.cpython-36m-x86_64-linux-gnu.so)
frame #3: + 0x17296 (0x7f03beb0d296 in /home/cody/PycharmProjects/FCOS/FCOS-master/fcos_core/_C.cpython-36m-x86_64-linux-gnu.so)
frame #4: + 0x1732e (0x7f03beb0d32e in /home/cody/PycharmProjects/FCOS/FCOS-master/fcos_core/_C.cpython-36m-x86_64-linux-gnu.so)
frame #5: + 0x146ca (0x7f03beb0a6ca in /home/cody/PycharmProjects/FCOS/FCOS-master/fcos_core/_C.cpython-36m-x86_64-linux-gnu.so)
The text was updated successfully, but these errors were encountered: