python run.py --dataset cornell --Ts 1.0 --topk 5 --lambd 0.9这行指令并没有顺利运行，请问您有遇到吗？

[manxiaoyu]

我的环境是python3.8.pytorch2.0.0,但再运行python run.py --dataset cornell --Ts 1.0 --topk 5 --lambd 0.9这行指令并没有顺利运行，出现了下面的错误，请问您有遇到吗？ Traceback (most recent call last): File "/home/visionx/anaconda3/envs/t2gnn/lib/python3.8/site-packages/scipy/sparse/_compressed.py", line 80, in init arg1 = np.asarray(arg1) File "/home/visionx/anaconda3/envs/t2gnn/lib/python3.8/site-packages/torch/_tensor.py", line 970, in array return self.numpy() TypeError: can't convert cuda:0 device type tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "run.py", line 21, in train = Train(args,repeat,acc_fea,acc_str,acc_stu) File "/media/visionx/monica/project24/T2-GNN/train.py", line 22, in init self.load_data() File "/media/visionx/monica/project24/T2-GNN/train.py", line 69, in load_data ppr_matrix = topk_ppr_matrix(sp.csr_matrix(self.ttadj, dtype=float), args.alpha_ppr, args.epsilon, File "/home/visionx/anaconda3/envs/t2gnn/lib/python3.8/site-packages/scipy/sparse/_compressed.py", line 82, in init raise ValueError("unrecognized {}_matrix constructor usage" ValueError: unrecognized csr_matrix constructor usage

[zhangailing]

同研究方向，改进这个模型，有意加微群交流吗？