Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.
Fusing model...
Switch model to deploy modality.
Traceback (most recent call last):
File "/content/YOLOv6/tools/infer.py", line 120, in
main(args)
File "/content/YOLOv6/tools/infer.py", line 115, in main
run(vars(args))
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, kwargs)
File "/content/YOLOv6/tools/infer.py", line 107, in run
inferer = Inferer(source, webcam, webcam_addr, weights, device, yaml, img_size, half)
File "/content/YOLOv6/yolov6/core/inferer.py", line 50, in init
self.model(torch.zeros(1, 3, self.img_size).to(self.device).type_as(next(self.model.model.parameters()))) # warmup
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, kwargs)
File "/content/YOLOv6/yolov6/layers/common.py", line 563, in forward
y, _ = self.model(im)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, *kwargs)
File "/content/YOLOv6/yolov6/models/yolo.py", line 35, in forward
x = self.backbone(x)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, kwargs)
File "/content/YOLOv6/yolov6/models/efficientrep.py", line 107, in forward
x = self.stem(x)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, kwargs)
File "/content/YOLOv6/yolov6/layers/common.py", line 248, in forward
return self.nonlinearity(self.se(self.rbr_reparam(inputs)))
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected input[1, 1, 3, 416] to have 3 channels, but got 1 channels instead
Environment
Google Colab,
Computer having Ubuntu 22.04 and Python 3.11
Search before asking
Notebook name
train-yolov6-object-detection-on-custom-data.ipynb
Bug
Fusing model... Switch model to deploy modality. Traceback (most recent call last): File "/content/YOLOv6/tools/infer.py", line 120, in
main(args)
File "/content/YOLOv6/tools/infer.py", line 115, in main
run(vars(args))
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, kwargs)
File "/content/YOLOv6/tools/infer.py", line 107, in run
inferer = Inferer(source, webcam, webcam_addr, weights, device, yaml, img_size, half)
File "/content/YOLOv6/yolov6/core/inferer.py", line 50, in init
self.model(torch.zeros(1, 3, self.img_size).to(self.device).type_as(next(self.model.model.parameters()))) # warmup
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, kwargs)
File "/content/YOLOv6/yolov6/layers/common.py", line 563, in forward
y, _ = self.model(im)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, *kwargs)
File "/content/YOLOv6/yolov6/models/yolo.py", line 35, in forward
x = self.backbone(x)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, kwargs)
File "/content/YOLOv6/yolov6/models/efficientrep.py", line 107, in forward
x = self.stem(x)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, kwargs)
File "/content/YOLOv6/yolov6/layers/common.py", line 248, in forward
return self.nonlinearity(self.se(self.rbr_reparam(inputs)))
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, *kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Given groups=1, weight of size [32, 3, 3, 3], expected input[1, 1, 3, 416] to have 3 channels, but got 1 channels instead
Environment
Google Colab, Computer having Ubuntu 22.04 and Python 3.11
Minimal Reproducible Example
No response
Additional
No response
Are you willing to submit a PR?