Wrong HiFiGAN's MPD?

[BridgetteSong]

1. for HiFiGAN's stable training, feature_loss of MPD should be computed, so in the each PD, it should return all convolution's outputs, not only the last one. But in each PD, it only returns the last output, and middle outputs are not saved. https://github.com/TensorSpeech/TensorFlowTTS/blob/136877136355c82d7ba474ceb7a8f133bd84767e/tensorflow_tts/models/hifigan.py#L309-L329
2. maybe like this:

out = [] for i, layer in enumerate(self.convs):

• x = layer(x)
• x = self.activation(x)
• out.append(tf.reshape(x, [shape[0], -1, min(self.filters * (self.filter_scales ** (i + 1)), self.max_filters)]))

x = self.conv_post(x) x = tf.reshape(x, [shape[0], -1, self.out_filters]) out.append(x) return out

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.