Not compiled with GPU support
ztb520 opened this issue · 9 comments
When I tried to run the demo, there was an error Not Compiled with GPU support. Is it because I'm using the CUDA version? I tried to use Cuda9.0 and Cuda10.1, but this error occurred in both cases. What version of CUDA is running in your environment?
Using tracking threshold for out threshold! 0.4
Fix size testing.
training chunk_sizes: [32]
input h w: 544 960
heads {'hm': 1, 'reg': 2, 'wh': 2, 'ltrb_amodal': 4}
weights {'hm': 1, 'reg': 1, 'wh': 0.1, 'ltrb_amodal': 0.1, 'cost_volume': 1.0}
head conv {'hm': [256], 'reg': [256], 'wh': [256], 'ltrb_amodal': [256]}
Creating model...
Using node type: (<class 'model.networks.dla.DeformConv'>, <class 'model.networks.dla.DeformConv'>)
Warning: No ImageNet pretrain!!
loaded ../models/mot_half.pth, epoch 70
OpenCV: FFMPEG: tag 0x44495658/'XVID' is not supported with codec id 12 and format 'mp4 / MP4 (MPEG-4 Part 14)'
OpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'
Initialize tracking!
Traceback (most recent call last):
File "demo.py", line 129, in
demo(opt)
File "demo.py", line 84, in demo
ret = detector.run(img)
File "/home/user/anaconda3/envs/TraDeS/src/lib/detector.py", line 127, in run
images, self.pre_images, self.pre_hms, return_time=True)
File "/home/user/anaconda3/envs/TraDeS/src/lib/detector.py", line 399, in process
output, current_feat = self.model(images, pre_images, pre_hms, inference_feats=self.inference_feats, addtional_pre_imgs=self.inference_preim, addtional_pre_hms=self.inference_prehm)
File "/home/user/anaconda3/envs/trades/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda3/envs/TraDeS/src/lib/model/networks/base_model.py", line 150, in forward
cur_feat = self.img2feats(x)
File "/home/user/anaconda3/envs/TraDeS/src/lib/model/networks/dla.py", line 603, in img2feats
x = self.dla_up(x)
File "/home/user/anaconda3/envs/trades/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda3/envs/TraDeS/src/lib/model/networks/dla.py", line 553, in forward
ida(layers, len(layers) -i - 2, len(layers))
File "/home/user/anaconda3/envs/trades/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda3/envs/TraDeS/src/lib/model/networks/dla.py", line 524, in forward
layers[i] = upsample(project(layers[i]))
File "/home/user/anaconda3/envs/trades/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda3/envs/TraDeS/src/lib/model/networks/dla.py", line 497, in forward
x = self.conv(x)
File "/home/user/anaconda3/envs/trades/lib/python3.6/site-packages/torch/nn/modules/module.py", line 541, in call
result = self.forward(*input, kwargs)
File "/home/user/anaconda3/envs/TraDeS/src/lib/model/networks/DCNv2/dcn_v2.py", line 128, in forward
self.deformable_groups)
File "/home/user/anaconda3/envs/TraDeS/src/lib/model/networks/DCNv2/dcn_v2.py", line 31, in forward
ctx.deformable_groups)
RuntimeError: Not compiled with GPU support (dcn_v2_forward at /home/user/anaconda3/envs/TraDeS/src/lib/model/networks/DCNv2/src/dcn_v2.h:35)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x47 (0x7f52fe1f9687 in /home/user/anaconda3/envs/trades/lib/python3.6/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) + 0x178 (0x7f52e9e83c18 in /home/user/anaconda3/envs/TraDeS/src/lib/model/networks/DCNv2/_ext.cpython-36m-x86_64-linux-gnu.so)
frame #2: + 0x193cb (0x7f52e9e913cb in /home/user/anaconda3/envs/TraDeS/src/lib/model/networks/DCNv2/_ext.cpython-36m-x86_64-linux-gnu.so)
frame #3: + 0x15c7c (0x7f52e9e8dc7c in /home/user/anaconda3/envs/TraDeS/src/lib/model/networks/DCNv2/_ext.cpython-36m-x86_64-linux-gnu.so)
frame #10: THPFunction_apply(_object, _object) + 0x9ff (0x7f532e54690f in /home/user/anaconda3/envs/trades/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
Aborted (core dumped)
exit status 134
The cuda installation command is shown in the INSTALL.md as:
conda install pytorch=1.3.1 torchvision=0.4.2 cudatoolkit=10.0.130 -c pytorch
I have completed downloading according to this command, but there is still such an error, which is inexplicable.
When I run the file setup.py, the following error occurs:No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda'
I followed the installation command to complete the download, and I also had this error. So I changed the environment and it ran successfully
python = 3.7
conda install pytorch=1.3 torchvision cudatoolkit=10.1 -c pytorch
I followed the installation command to complete the download, and I also had this error. So I changed the environment and it ran successfully
python = 3.7
conda install pytorch=1.3 torchvision cudatoolkit=10.1 -c pytorch
I successfully run the program, but now there is a new error：Aborted (core dumped)exit status 134, when frame=200.Have you ever met this mistake？
I followed the installation command to complete the download, and I also had this error. So I changed the environment and it ran successfully
python = 3.7
conda install pytorch=1.3 torchvision cudatoolkit=10.1 -c pytorchI successfully run the program, but now there is a new error：Aborted (core dumped)exit status 134, when frame=200.Have you ever met this mistake？
I'm sorry, I didn't encounter this problem
I followed the installation command to complete the download, and I also had this error. So I changed the environment and it ran successfully
python = 3.7
conda install pytorch=1.3 torchvision cudatoolkit=10.1 -c pytorchI successfully run the program, but now there is a new error：Aborted (core dumped)exit status 134, when frame=200.Have you ever met this mistake？
I'm sorry, I didn't encounter this problem
What is the final frame when you run the MOT demo? I can tell from the code that it looks like the program is over when frame = 200.
The cuda installation command is shown in the INSTALL.md as:
conda install pytorch=1.3.1 torchvision=0.4.2 cudatoolkit=10.0.130 -c pytorch
When I run the following command：sh experiments/mot17_train.sh，There's an error：FileNotFoundError: [Errno 2] No such file or directory: '/home/user/TraDeS_ROOT/src/lib/../../data/mot17/annotations/train_half.json'.
After running the command, I see the program looking for data:Using MOT 17 17halftrain
ann_file train_half.json
==> initializing train data from /home/user/TraDeS_ROOT/src/lib/../../data/mot17/annotations/train_half.json,
images from /home/user/TraDeS_ROOT/src/lib/../../data/mot17/train ...
loading annotations into memory...
But I can't find these files. There are no files in the folder. Why is that?