与 GPU 一起使用时，packed_pa​​dded_sequence 会出错

Question

I am trying to set up an RNN capable of utilizing a GPU but packed_padded_sequence gives me a

RuntimeError: 'lengths' argument should be a 1D CPU int64 tensor

here is how I direct gpu computing

parser = argparse.ArgumentParser(description='Trainer')
parser.add_argument('--disable-cuda', action='store_true',
                    help='Disable CUDA')
args = parser.parse_args()
args.device = None
if not args.disable_cuda and torch.cuda.is_available():
    args.device = torch.device('cuda')
    torch.set_default_tensor_type(torch.cuda.FloatTensor)
else:
    args.device = torch.device('cpu')

here is the relevant part of the code.

def Tensor_length(track):
    """Finds the length of the non zero tensor"""
    return int(torch.nonzero(track).shape[0] / track.shape[1])
.
.
.
def forward(self, tracks, leptons):
        self.rnn.flatten_parameters()
        # list of event lengths
        n_tracks = torch.tensor([Tensor_length(tracks[i])
                                 for i in range(len(tracks))])
        sorted_n, indices = torch.sort(n_tracks, descending=True)
        sorted_tracks = tracks[indices].to(args.device)
        sorted_leptons = leptons[indices].to(args.device)
        # import pdb; pdb.set_trace()
        output, hidden = self.rnn(pack_padded_sequence(sorted_tracks,
                                                       lengths=sorted_n.cpu().numpy(),
                                                       batch_first=True)) # this gives the error

        combined_out = torch.cat((sorted_leptons, hidden[-1]), dim=1)
        out = self.fc(combined_out)  # add lepton data to the matrix
        out = self.softmax(out)
        return out, indices  # passing indices for reorganizing truth

I have tried everything from casting sorted_n to a long tensor to having it be a list, but i aways seem to get the same error. I have not worked with pytorch on gpu before and any advice will be greatly appreciated.

Thanks!

Answer 1

I assume you are using the GPU and probably on the Google Colab. Check yours device

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
device

you may solve this error by downgrading the torch version, if you are using colab the following command will help you:

!pip install torch==1.6.0 torchvision==0.7.0

once you downgrade the torch, this error of padded length will go.