Facing Error while executing

[ayamgupta]

Hey I am new to this can you help me out with the error?

YOLOv5 🚀 1888663 torch 1.13.1+cu117 CPU

Fusing layers...
Model Summary: 308 layers, 21041679 parameters, 0 gradients
WARNING: --img-size [720, 1280] must be multiple of max stride 32, updating to [736, 1280]
Traceback (most recent call last):
File "/home/ayamgupta/ps/PedestrianSpeedEstimator/track.py", line 325, in
detect(opt)
File "/home/ayamgupta/ps/PedestrianSpeedEstimator/track.py", line 145, in detect
pred = model(img, augment=opt.augment, visualize=visualize)
File "/home/ayamgupta/mambaforge/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/home/ayamgupta/ps/PedestrianSpeedEstimator/yolov5/models/common.py", line 384, in forward
y = self.model(im) if self.jit else self.model(im, augment=augment, visualize=visualize)
File "/home/ayamgupta/mambaforge/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/home/ayamgupta/ps/PedestrianSpeedEstimator/./yolov5/models/yolo.py", line 126, in forward
return self._forward_once(x, profile, visualize) # single-scale inference, train
File "/home/ayamgupta/ps/PedestrianSpeedEstimator/./yolov5/models/yolo.py", line 149, in _forward_once
x = m(x) # run
File "/home/ayamgupta/mambaforge/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/home/ayamgupta/mambaforge/lib/python3.10/site-packages/torch/nn/modules/upsampling.py", line 157, in forward
recompute_scale_factor=self.recompute_scale_factor)
File "/home/ayamgupta/mambaforge/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1269, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor'

[shriram1998]

Hi,
Seems to be an issue with yolov5 package and its dependencies. You could search for possible solutions. Here is a good starting point (ultralytics/yolov5#6948)

[ayamgupta]

Thanks. resolved the issue. also the latest pytorch version conflicts. It works perfectly now.