Question 1: I would like to try to run the reference_segmentation.py file, but the following error occurs "RuntimeError: Can't call numpy() on Tensor that requires grad. use tensor.detach(). numpy() instead.". As shown in the image below.
![Uploading WechatIMG599.jpg…]()
Then I modified ax.add_patch(rect) to ax.add_patch(rect.detach().numpy()). But new error "AttributeError: 'Rectangle' object has no attribute 'detach'" appears.
![Uploading WechatIMG600.jpg…]()
I would like to ask how to solve this problem. The image format I am using is png.
Question 2: While segmenting the CT images, I found that there is a corresponding tasks file in both test and train datasets. How is that masks file obtained?
yixuanli1230
commented
10 months ago
Question 1: I would like to try to run the reference_segmentation.py file, but the following error occurs "RuntimeError: Can't call numpy() on Tensor that requires grad. use tensor.detach(). numpy() instead.". As shown in the image below. ![Uploading WechatIMG599.jpg…]()
Then I modified ax.add_patch(rect) to ax.add_patch(rect.detach().numpy()). But new error "AttributeError: 'Rectangle' object has no attribute 'detach'" appears. ![Uploading WechatIMG600.jpg…]()
I would like to ask how to solve this problem. The image format I am using is png.
Question 2: While segmenting the CT images, I found that there is a corresponding tasks file in both test and train datasets. How is that masks file obtained?