AttributeError: 'float' object has no attribute 'unsqueeze'

[ljx761795750]

Dear author, hello.
Thank you for your contribution. I encountered some problems when you provided the code above github.

Traceback (most recent call last):
File "./../../..///test.py", line 137, in
mean_acc = test(model, test_loader,label_names,cuda=args.cuda)
File "/home/li/anaconda3/envs/3D/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(args, kwargs)
File "./../../..///test.py", line 31, in test
outputs = model(batch_1, batch_2)
File "/home/li/anaconda3/envs/3D/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(input, kwargs)
File "/mnt/xishu/test2/munegc-master///twostream_network.py", line 114, in forward
data = self.multimodal_gp_fusion(data_b1, data_b2)
File "/home/li/anaconda3/envs/3D/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(input, kwargs)
File "/mnt/xishu/test2/munegc-master//***/twostream_network.py", line 29, in forward
cluster = torch_geometric.nn.voxel_grid(pos, batch, self.pool_rad, start=start, end=end)
File "/home/li/anaconda3/envs/3D/lib/python3.8/site-packages/torch_geometric/nn/pool/voxel_grid.py", line 58, in voxel_grid
pos = torch.cat([pos, batch.unsqueeze(-1).type_as(pos)], dim=-1)
AttributeError: 'float' object has no attribute 'unsqueeze'

[EdisonLeeeee]

Thanks for reporting. Would you mind providing a code example to reproduce this bug? I'm afraid I cannot figure it out based on your traceback logs.