monkeycc
monkeycc
我也遇到了这个问题 只要升级到paddleX2.0 就会报这个错
一样不行，我怀疑是图片太大了 "imageHeight": 2304, "imageWidth": 2664
```python masks = result.masks.numpy() # Ensure masks are in numpy array File "E:\anaconda3\envs\intsoft_310\lib\site-packages\ultralytics\engine\results.py", line 47, in numpy return self if isinstance(self.data, np.ndarray) else self.__class__(self.data.numpy(), self.orig_shape) TypeError: can't convert cuda:0 device...
```PYTHON for result in results: masks = result.masks.cpu().numpy() # Move tensor to CPU, then convert to numpy ``` 'Masks' object has no attribute 'xy'. See valid attributes below. A class...
Useless ``` 'Masks' object has no attribute 'xy'. See valid attributes below. A class for storing and manipulating detection masks. Attributes: xy (list): A list of segments in pixel coordinates....
I know the reason Default conversion of png images Should be converted to a jpg image
yolov8-cls +1
Thank you, very valuable for reference The problem has been resolved But I'm not sure why this is happening My train model is 1280 `imgsz=1280` But when reasoning, it must...
Training model imgsz=1280 predict imgsz=640 normal predict imgsz=1280 There is an issue with the recognition rate! What is the reason Shouldn't we also use imgsz=1280 for predict