export yolov8-lite-s and yolov8-lite-t error

[pcb9382]

yolo mode=export model=yolov8-lite-s.pt format=onnx simplify=True batch=1
Traceback (most recent call last):
File "/home/pcb/.local/bin/yolo", line 8, in
sys.exit(entrypoint())
File "/home/pcb/.local/lib/python3.8/site-packages/ultralytics/yolo/cfg/init.py", line 378, in entrypoint
model = YOLO(model, task=task)
File "/home/pcb/.local/lib/python3.8/site-packages/ultralytics/yolo/engine/model.py", line 107, in init
self._load(model, task)
File "/home/pcb/.local/lib/python3.8/site-packages/ultralytics/yolo/engine/model.py", line 156, in _load
self.model, self.ckpt = attempt_load_one_weight(weights)
File "/home/pcb/.local/lib/python3.8/site-packages/ultralytics/nn/tasks.py", line 578, in attempt_load_one_weight
ckpt, weight = torch_safe_load(weight) # load ckpt
File "/home/pcb/.local/lib/python3.8/site-packages/ultralytics/nn/tasks.py", line 518, in torch_safe_load
return torch.load(file, map_location='cpu'), file # load
File "/home/pcb/.local/lib/python3.8/site-packages/torch/serialization.py", line 607, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/home/pcb/.local/lib/python3.8/site-packages/torch/serialization.py", line 882, in _load
result = unpickler.load()
File "/home/pcb/.local/lib/python3.8/site-packages/torch/serialization.py", line 875, in find_class
return super().find_class(mod_name, name)
AttributeError: Can't get attribute 'StemBlock' on <module 'ultralytics.nn.modules' from '/home/pcb/.local/lib/python3.8/site-packages/ultralytics/nn/modules/init.py'>

[yantianj]

hi, [pcb9382]

我也尝试导出模型到ONNX
I also tried exporting the model to ONNX.
期间报了好几个错
During this period, several errors were reported.

1. AttributeError: Can't get attribute 'StemBlock' on <module 'ultralytics.nn.modules' from '/home/pcb/.local/lib/python3.8/site-packages/ultralytics/nn/modules/init.py'>

在作者自己的ultralytics里是有StemBlock这个函数得，但导出时我们安装使用是官方的包 来自于 命令“pip install ultralytics”
There is a function called StemBlock in the author's own ultralytics, but when exporting, we install and use an official package from the command "pip install ultralytics"

解决办法:
solution:

copy :
xxx\yolov8-face\ultralytics\nn\modules\block.py
xxx\yolov8-face\ultralytics\nn\modules_init_.py
to :
xxx\anaconda\envs\yolov8\Lib\site-packages\ultralytics\nn\modules\block.py
xxx\anaconda\envs\yolov8\Lib\site-packages\ultralytics\nn\modules_init_.py

[yantianj]

I want to export the model as onnx opset 11

I succeeded, and all the steps to try are as follows:

1. pip install torch==1.8.1 torchvision==0.9.1 torchaudio==0.8.1 -i https://pypi.doubanio.com/simple
   answer from: TypeError: conv2d() received an invalid combination of arguments - got (Tensor, Parameter, NoneType, tuple, tuple, tuple, int), but expected one of: we0091234/yolov8-plate#2

2. pip install ultralytics==8.0.134 -i https://pypi.tuna.tsinghua.edu.cn/simple
   version from: xxx/yolov8-face/ultralytics/init.py

copy :
xxx\yolov8-face\ultralytics\nn\modules\block.py
xxx\yolov8-face\ultralytics\nn\modules_init_.py
to :
xxx\anaconda\envs\yolov8\Lib\site-packages\ultralytics\nn\modules\block.py
xxx\anaconda\envs\yolov8\Lib\site-packages\ultralytics\nn\modules_init_.py

4. code:

export.py

from ultralytics import YOLO

model = YOLO("xxx/yolov8n-face.pt")
success = model.export(format="onnx", opset=11, simplify=True)