'Detect' object has no attribute 'm' about yolo_tracking HOT 10 CLOSED

It will be very hard to help you with this little information. Could you provide the complete error message?

from yolo_tracking.

self.update(yaml.load(fo.read()))
Using CUDA device0 _CudaDeviceProperties(name='GeForce MX150', total_memory=2002MB)

/home/lyx/anaconda3/lib/python3.7/site-packages/torch/serialization.py:657: SourceChangeWarning: source code of class 'models.yolo.Model' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/home/lyx/anaconda3/lib/python3.7/site-packages/torch/serialization.py:657: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/home/lyx/anaconda3/lib/python3.7/site-packages/torch/serialization.py:657: SourceChangeWarning: source code of class 'models.yolo.Detect' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
1/1: 0... success (640x480 at 30.00 FPS).

Traceback (most recent call last):
File "track.py", line 247, in
detect(args)
File "track.py", line 122, in detect
_ = model(img.half() if half else img) if device.type != 'cpu' else None # run once
File "/home/lyx/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "./yolov5/models/yolo.py", line 110, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "./yolov5/models/yolo.py", line 130, in forward_once
x = m(x) # run
File "/home/lyx/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "./yolov5/models/yolo.py", line 37, in forward
x[i] = self.mi # conv
File "/home/lyx/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 594, in getattr
type(self).name, name))
AttributeError: 'Detect' object has no attribute 'm'
terminate called without an active exception

And pytorch=1.5.0 cuda=10.2 python=3.7
The reason why I use pytorch 1.5.0 is that I can not run original yolov5 when I update my pytorch to 1.6.0

from yolo_tracking.

self.update(yaml.load(fo.read()))
Using CUDA device0 _CudaDeviceProperties(name='GeForce MX150', total_memory=2002MB)

/home/lyx/anaconda3/lib/python3.7/site-packages/torch/serialization.py:657: SourceChangeWarning: source code of class 'models.yolo.Model' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/home/lyx/anaconda3/lib/python3.7/site-packages/torch/serialization.py:657: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/home/lyx/anaconda3/lib/python3.7/site-packages/torch/serialization.py:657: SourceChangeWarning: source code of class 'models.yolo.Detect' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
1/1: 0... success (640x480 at 30.00 FPS).

Traceback (most recent call last):
File "track.py", line 247, in
detect(args)
File "track.py", line 122, in detect
_ = model(img.half() if half else img) if device.type != 'cpu' else None # run once
File "/home/lyx/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "./yolov5/models/yolo.py", line 110, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "./yolov5/models/yolo.py", line 130, in forward_once
x = m(x) # run
File "/home/lyx/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in call
result = self.forward(*input, **kwargs)
File "./yolov5/models/yolo.py", line 37, in forward
x[i] = self.mi # conv
File "/home/lyx/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 594, in getattr
type(self).name, name))
AttributeError: 'Detect' object has no attribute 'm'
terminate called without an active exception

And pytorch=1.5.0 cuda=10.2 python=3.7
The reason why I use pytorch 1.5.0 is that I can not run original yolov5 when I update my pytorch to 1.6.0

And I use python3.8 and pytorch 1.6.0, I met the same problem.

from yolo_tracking.

同样遇到这个问题，有人解决了吗？

from yolo_tracking.

Traceback (most recent call last):
File "track.py", line 247, in
detect(args)
File "track.py", line 122, in detect
_ = model(img.half() if half else img) if device.type != 'cpu' else None # run once
File "/home/jie311/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "./yolov5/models/yolo.py", line 100, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "./yolov5/models/yolo.py", line 120, in forward_once
x = m(x) # run
File "/home/jie311/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "./yolov5/models/yolo.py", line 27, in forward
x[i] = self.mi # conv
File "/home/jie311/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 591, in getattr
type(self).name, name))
AttributeError: 'Detect' object has no attribute 'm'

I encountered this problem, too. Need I upgrade my pytorch from 1.2.0 to 1.6.0 ? Or is it about my python version 3.6.10 ?Thanks @mikel-brostrom

请问有哪位大佬解决了这个问题么？可以的话交流一下谢谢！

from yolo_tracking.

Make sure that ALL the requirements are fulfilled: Python >= 3.8, PyTorch >= 1.6 etc.
Then make sure both your code and models are up to date. If in doubt, simply start from a clean slate: reclone the repo and download new weights

from yolo_tracking.

For more info on this specific error you could check:

• ultralytics/yolov5#690

from yolo_tracking.

For more info on this specific error you could check:

• ultralytics/yolov5#690

yes solve it Thx

from yolo_tracking.

I just updated yolov5. That may help as well

from yolo_tracking.

I encountered this same error myself yesterday while updating yolov5. I updated the code but didn't update the models, so... #10 (comment)

from yolo_tracking.