gpu

[henbucuoshanghai]

ile "/home/fengmap/FairMOT/DCNv2/dcn_v2.py", line 31, in forward ctx.deformable_groups) RuntimeError: Not compiled with GPU support (dcn_v2_forward at /home/fengmap/FairMOT/DCNv2/src/dcn_v2.h:35) frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) + 0x6d (0x7fa74f6f41cd in /home/fengmap/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/lib/libc10.so) frame #1: dcn_v2_forward(at::Tensor const&, at::Tensor const&, at::Tensor const&, at::Tensor const&, at::Tensor const&, int, int, int, int, int, int, int, int, int) + 0x1d4 (0x7fa7135b2b84 in /home/fengmap/FairMOT/DCNv2/_ext.cpython-37m-x86_64-linux-gnu.so) frame #2: + 0x1868b (0x7fa7135c068b in /home/fengmap/FairMOT/DCNv2/_ext.cpython-37m-x86_64-linux-gnu.so) frame #3: + 0x15157 (0x7fa7135bd157 in /home/fengmap/FairMOT/DCNv2/_ext.cpython-37m-x86_64-linux-gnu.so) frame #8: THPFunction_apply(_object*, _object*) + 0xa56 (0x7fa771fb75f6 in /home/fengmap/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/lib/libtorch_python.so)

[henbucuoshanghai]

demo的时候 出现的 请问怎么回事

[ifzhang]

It seems that you do not compile DCNv2 successfully. You should compile DCNv2 first.

[xiaoaliu]

Installed /home/lee/FairMOT1/DCNv2 Processing dependencies for DCNv2==0.1 Finished processing dependencies for DCNv2==0.1 2021-09-20 10:58:35 [INFO]: Processing frame 0 (100000.00 fps) Traceback (most recent call last): File "demo.py", line 43, in demo(opt) File "demo.py", line 30, in demo eval_seq(opt, dataloader, 'mot', result_filename, File "/home/lee/FairMOT1/src/track.py", line 90, in eval_seq online_targets = tracker.update(blob, img0) File "/home/lee/FairMOT1/src/lib/tracker/multitracker.py", line 243, in update output = self.model(im_blob)[-1] File "/home/lee/anaconda3/envs/FairMOT/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/lee/FairMOT1/src/lib/models/networks/pose_dla_dcn.py", line 472, in forward x = self.dla_up(x) File "/home/lee/anaconda3/envs/FairMOT/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/lee/FairMOT1/src/lib/models/networks/pose_dla_dcn.py", line 411, in forward ida(layers, len(layers) -i - 2, len(layers)) File "/home/lee/anaconda3/envs/FairMOT/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/lee/FairMOT1/src/lib/models/networks/pose_dla_dcn.py", line 384, in forward layers[i] = upsample(project(layers[i])) File "/home/lee/anaconda3/envs/FairMOT/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/lee/FairMOT1/src/lib/models/networks/pose_dla_dcn.py", line 355, in forward x = self.conv(x) File "/home/lee/anaconda3/envs/FairMOT/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/lee/FairMOT1/DCNv2/dcn_v2.py", line 161, in forward return dcn_v2_conv( File "/home/lee/FairMOT1/DCNv2/dcn_v2.py", line 23, in forward output = _backend.dcn_v2_forward( RuntimeError: Not compiled with GPU support

[xiaoaliu]

请问下 显示我已成功编译DCN 为什么还是没有GPU

[goldentimecoolk]

请问下 显示我已成功编译DCN 为什么还是没有GPU

@xiaoaliu 我有同样的问题，请问您解决了吗？