error while evaluation via vae_vcc

Open Ashbajawed opened this issue 3 years ago • 0 comments

I'm getting this error RuntimeError: expected scalar type Long but found Float

full trace:

RuntimeError Traceback (most recent call last) in 6 print( mulaw(audio_split).dtype, audio_split.dtype) 7 # Voice conversion ----> 8 out_mulaw = builder.convert(x=mulaw(audio_split.type(torch.LongTensor)), y=target_speaker_id.type(torch.LongTensor))

~/danish/new/voice-conversion/experiment_builders/vae_builder.py in convert(self, x, y) 242 y = y.to(self.device) 243 --> 244 x_out, _, _ = self.model.forward(x, y) # forward the data through the model 245 246 return torch.argmax(x_out.data, dim=1)

~/danish/new/voice-conversion/models/vae.py in forward(self, input, speaker) 106 def forward(self, input, speaker): 107 # pdb.set_trace() --> 108 z_e = self.encoder(input) 109 110 # Flatten z_e

~/anaconda3/envs/testing_2/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) 725 result = self._slow_forward(*input, **kwargs) 726 else: --> 727 result = self.forward(*input, **kwargs) 728 for hook in itertools.chain( 729 _global_forward_hooks.values(),

~/danish/new/voice-conversion/models/common_networks.py in forward(self, input) 56 out = input 57 for i in range(len(self.kernel_sizes)-1): ---> 58 out = self.layer_dict'conv_{}'.format(i) 59 60 out = self.final_conv(out)

~/danish/new/voice-conversion/models/common_layers.py in forward(self, input) 85 86 def forward(self, input): ---> 87 out = self.conv(input) 88 conv_out = self.ln(out) 89 return F.leaky_relu(out, negative_slope=0.02)

~/anaconda3/envs/testing_2/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input) 257 _single(0), self.dilation, self.groups) 258 return F.conv1d(input, self.weight, self.bias, self.stride, --> 259 self.padding, self.dilation, self.groups) 260 261

RuntimeError: expected scalar type Long but found Float

Jan 18 '22 11:01 Ashbajawed