Closed SINHAPIYUSH closed 4 years ago
Never mind, solved the issue after changing file: tracker.py line no: 61 ----------> blob = torch.from_numpy(img).cuda().unsqueeze(0) to this ----------------> blob = torch.from_numpy(img).cpu().unsqueeze(0)
Never mind, solved the issue after changing file: tracker.py line no: 61 ----------> blob = torch.from_numpy(img).cuda().unsqueeze(0) to this ----------------> blob = torch.from_numpy(img).cpu().unsqueeze(0)
Hi, am trying to implement it on CPU but not successful, getting stuck with DCNv2. Any suggestions on how to take it up?
Thanks in advance.
Hi, I am facing an error while following the steps mention in the readme.
When I try to run the demo command below: cd src python demo.py mot --load_model ../models/all_dla34.pth --conf_thres 0.4
I am facing the below error: python demo.py mot --load_model ../models/all_dla34.pth --conf_thres 0.4 Fix size testing. training chunk_sizes: [6, 6] The output will be saved to /home/npu/Downloads/FAIRMOT_ROOT/src/lib/../../exp/mot/default heads {'hm': 1, 'wh': 2, 'id': 512, 'reg': 2} 2020-06-23 09:36:20 [INFO]: Starting tracking... Lenth of the video: 1500 frames Creating model... loaded ../models/all_dla34.pth, epoch 10 Traceback (most recent call last): File "demo.py", line 40, in
demo(opt)
File "demo.py", line 30, in demo
eval_seq(opt, dataloader, 'mot', result_filename, save_dir=frame_dir, show_image=False, frame_rate=frame_rate)
File "/home/npu/Downloads/FAIRMOT_ROOT/src/track.py", line 51, in eval_seq
tracker = JDETracker(opt, frame_rate=frame_rate)
File "/home/npu/Downloads/FAIRMOT_ROOT/src/lib/tracker/multitracker.py", line 179, in init
self.model = self.model.to(opt.device)
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 432, in to
return self._apply(convert)
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 208, in _apply
module._apply(fn)
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 208, in _apply
module._apply(fn)
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 208, in _apply
module._apply(fn)
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 230, in _apply
param_applied = fn(param)
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/nn/modules/module.py", line 430, in convert
return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/cuda/init.py", line 178, in _lazy_init
_check_driver()
File "/home/npu/anaconda3/envs/FairMOT/lib/python3.7/site-packages/torch/cuda/init.py", line 99, in _check_driver
http://www.nvidia.com/Download/index.aspx""")
AssertionError:
Found no NVIDIA driver on your system. Please check that you
have an NVIDIA GPU and installed a driver from
http://www.nvidia.com/Download/index.aspx
I am using: VMware® Workstation 14 Pro ubuntu-16.04.6-desktop-amd64
I want to run the model on CPU. I have enabled the option in opts.py as -1 for CPU. However I am still getting the above error. Is anyone able to run it on CPU?
Thanks in advance.