Traceback (most recent call last):
File "train.py", line 616, in
train(hyp, opt, device, tb_writer)
File "train.py", line 95, in train
model = Model(opt.cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
File "/media/kb541/ruanpuchao/yolov7_train/models/yolo.py", line 717, in init
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
File "/media/kb541/ruanpuchao/yolov7_train/models/yolo.py", line 774, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "/media/kb541/ruanpuchao/yolov7_train/models/yolo.py", line 800, in forward_once
x = m(x) # run
File "/home/undergraduate/anaconda3/envs/yolov7p/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/media/kb541/ruanpuchao/yolov7_train/models/common.py", line 2037, in forward
x = self.dcnv3(x)
File "/home/undergraduate/anaconda3/envs/yolov7p/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/media/kb541/ruanpuchao/yolov7_train/models/ops_dcnv3/modules/dcnv3.py", line 125, in forward
x = DCNv3Function.apply(
File "/home/undergraduate/anaconda3/envs/yolov7p/lib/python3.8/site-packages/torch/cuda/amp/autocast_mode.py", line 110, in decorate_fwd
return fwd(*args, **kwargs)
File "/media/kb541/ruanpuchao/yolov7_train/models/ops_dcnv3/functions/dcnv3_func.py", line 39, in forward
output = DCNv3.dcnv3_forward(
RuntimeError: Not implemented on the CPU
Does anyone know what the reason for this error is? I would appreciate it if you help me solve this issue.
You can change core_op='DCNv3' to core_op='DCNv3_pytorch' in the config to support CPU.
do you hava solved this error?
Have you solved the problem? I have also encountered a similar problem, and I hope to get your clarification.
请问您解决这个问题了吗？我也遇到了类似的问题，希望得到您的解惑。
do you hava solved this error?
OpenGVLab
