[ONNX]RuntimeError: Unexpected node type: onnx::Cast #47182
Description
❓convert faild
class Decoder(nn.Module):
def __init__(self, N, L):
super(Decoder, self).__init__()
# Hyper-parameter
self.N, self.L = N, L
# Components
self.basis_signals = nn.Linear(N, L, bias=False)
def forward(self, mixture_w, est_mask):
"""
Args:
mixture_w: [M, N, K]
est_mask: [M, C, N, K]
Returns:
est_source: [M, C, T]
"""
# D = W * M
source_w = torch.unsqueeze(mixture_w, 1) * est_mask # [M, C, N, K]
source_w = torch.transpose(source_w, 2, 3) # [M, C, K, N]
# S = DV
est_source = self.basis_signals(source_w) # [M, C, K, L]
est_source = overlap_and_add(est_source, self.L // 2) # M x C x T
return est_sourceThis is the model which I converted. It has two inputs, and it's a Linear NN. As I know onnx.export support mutiple inputs.
So I convert it with the following code:
model = ConvTasNet.load_model(args.model_path)
model.eval()
Decoder = model.decoder
torch.onnx.export(Decoder, (separator_input, decoder_input),
decoder_path,
export_params=True )
But I got this error.
RuntimeError: Unexpected node type: onnx::Cast
Further information
Pytorch 1.7
cc @houseroad @spandantiwari @lara-hdr @BowenBao @neginraoof