vdemichev / DiaNN

DIA-NN - a universal automated software suite for DIA proteomics data analysis.
Other
283 stars 53 forks source link

DIA-NN Libtorch error #1193

Closed shilly99 closed 1 month ago

shilly99 commented 1 month ago

I am making a phospho spec library and DIA-NN is crashing every time I do it. Here are the parameters I am using: Missed cleavage: 1 Max variable modifications:3, with only phospho and C- carbamidomethylation checked. Precursor charge: 2-3 pep length: 7-30

I am also getting this error:

Libtorch error: The following operation failed in the TorchScript interpreter. Traceback of TorchScript, serialized code (most recent call last): File "code/torch.py", line 51, in forward hidden = torch.zeros([_9, _10, hidden_size], dtype=None, layout=None, device=torch.device(device0)) rnn = self.rnn output, hidden0, = (rnn).forward__0(conv1, hidden, )


    prepare = self.prepare
    prepare0 = torch.rrelu((prepare).forward(output, ))
  File "code/__torch__/torch/nn/modules/rnn.py", line 50, in forward__0
    _flat_weights = self._flat_weights
    training = self.training
    _3, _4 = torch.gru(input, hx0, _flat_weights, True, 2, 0.29999999999999999, training, True, True)
             ~~~~~~~~~ <--- HERE
    _5 = (_3, (self).permute_hidden(_4, None, ))
    return _5

Traceback of TorchScript, original code (most recent call last):
  File "<ipython-input-16-0dd9b29dfda4>", line 32, in forward

        hidden = torch.zeros(self.directions * self.layers, input.size(0), self.hidden_size, device = self.device)
        output, hidden = self.rnn(conv, hidden)
                         ~~~~~~~~ <--- HERE
        prepare = torch.rrelu(self.prepare(output))
        out = self.out(prepare)
  File "C:\ProgramData\Anaconda3\lib\site-packages\torch\nn\modules\rnn.py", line 849, in forward__0
        self.check_forward_args(input, hx, batch_sizes)
        if batch_sizes is None:
            result = _VF.gru(input, hx, self._flat_weights, self.bias, self.num_layers,
                     ~~~~~~~ <--- HERE
                             self.dropout, self.training, self.bidirectional, self.batch_first)
        else:
vdemichev commented 1 month ago

Hi,

How does the DIA-NN log look like?

Best, Vadim

shilly99 commented 1 month ago

It was happening due to low storage on my system. It has been resolved now. You can close this issue.