ScaledYOLOv4
ScaledYOLOv4 copied to clipboard
Error in generating prediction with torch and cuda version of 1.11.0+cu113 in google colab
I am trying to inference with model on colab it throws following error -
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
[<ipython-input-7-07bcaca33852>](https://localhost:8080/#) in <module>()
12 res_img = cv2.resize(image, (512, 512))
13 pre_img = preprocess(res_img)
---> 14 prediction = model(pre_img)[0]
15 result = postprocess(prediction, res_img, pre_img, height, width,
16 conf_thres, iou_thres)
5 frames
[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
[/content/drive/MyDrive/tablecell_detection/ScaledYOLOv4/models/yolo.py](https://localhost:8080/#) in forward(self, x, augment,
profile)
107 return torch.cat(y, 1), None # augmented inference, train
108 else:
--> 109 return self.forward_once(x, profile) # single-scale inference, train
110
111 def forward_once(self, x, profile=False):
[/content/drive/MyDrive/tablecell_detection/ScaledYOLOv4/models/yolo.py](https://localhost:8080/#) in forward_once(self, x, profile)
127 print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
128
--> 129 x = m(x) # run
130 y.append(x if m.i in self.save else None) # save output
131
[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/upsampling.py](https://localhost:8080/#) in forward(self, input)
152 def forward(self, input: Tensor) -> Tensor:
153 return F.interpolate(input, self.size, self.scale_factor, self.mode, self.align_corners,
--> 154 recompute_scale_factor=self.recompute_scale_factor)
155
156 def extra_repr(self) -> str:
[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in __getattr__(self, name)
1184 return modules[name]
1185 raise AttributeError("'{}' object has no attribute '{}'".format(
-> 1186 type(self).__name__, name))
1187
1188 def __setattr__(self, name: str, value: Union[Tensor, 'Module']) -> None:
AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor'
Colab version pytorch and cuda - 1.11.0+cu113
Hi, same issue here. @Atul997 any solution so far?