1 write to dense
Microsoft.ML.TorchSharp (1)
Roberta\Modules\AttentionOutput.cs (1)
24dense = torch.nn.Linear(hiddenSize, hiddenSize, true);
2 references to dense
Microsoft.ML.TorchSharp (2)
Roberta\Modules\AttentionOutput.cs (2)
33hiddenStates = dense.forward(hiddenStates); 45dense.Dispose();