windows复现trades时运行demo报错RuntimeError: Not compiled with GPU support
(trades) D:\machinelearning\TraDeS-master\src>python demo.py tracking --dataset mot --load_model ../models/mot_half.pth --demo ../videos/mot_mini.mp4 --pre_hm --ltrb_amodal --pre_thresh 0.5 --track_thresh 0.4 --inference --clip_len 3 --trades --save_video --resize_video --input_h 544 --input_w 960
Running tracking
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 <module>
demo(opt)
File "demo.py", line 84, in demo
ret = detector.run(img)
File "D:\machinelearning\TraDeS-master\src\lib\detector.py", line 128, in run
images, self.pre_images, self.pre_hms, return_time=True)
File "D:\machinelearning\TraDeS-master\src\lib\detector.py", line 355, 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 "D:\Anaconda3\envs\trades\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "D:\machinelearning\TraDeS-master\src\lib\model\networks\base_model.py", line 164, in forward
cur_feat = self.img2feats(x)
File "D:\machinelearning\TraDeS-master\src\lib\model\networks\dla.py", line 603, in img2feats
x = self.dla_up(x)
File "D:\Anaconda3\envs\trades\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "D:\machinelearning\TraDeS-master\src\lib\model\networks\dla.py", line 553, in forward
ida(layers, len(layers) -i - 2, len(layers))
File "D:\Anaconda3\envs\trades\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "D:\machinelearning\TraDeS-master\src\lib\model\networks\dla.py", line 524, in forward
layers[i] = upsample(project(layers[i]))
File "D:\Anaconda3\envs\trades\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "D:\machinelearning\TraDeS-master\src\lib\model\networks\dla.py", line 497, in forward
x = self.conv(x)
File "D:\Anaconda3\envs\trades\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__
result = self.forward(*input, **kwargs)
File "D:\machinelearning\TraDeS-master\src\lib\model\networks\DCNv2\dcn_v2.py", line 128, in forward
self.deformable_groups)
File "D:\machinelearning\TraDeS-master\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 d:\machinelearning\trades-master\src\lib\model\networks\dcnv2\src\dcn_v2.h:35)
dcnv2已经编译成功，cuda装的是官方配置的cuda10.0和对应cudnn，pytorch也装的是官方配置要求的torch1.3.1和torchvision0.4.2，GPU版，cudatoolkit10.0，vs2017
怎么办呀一直解决不了，我电脑显卡gtx1060的，求指点！！