loss functions updates

config.json

@@ -29,7 +29,7 @@
         "url": "tcp:\/\/localhost:54321"
     },
 
-    "reinit_layers": ["model.decoder.attention_layer"],
+    "reinit_layers": ["model.decoder.attention_layer"],  //set which layers to be reinitialized in finetunning. Only used if --restore_model is provided.
 
     "model": "Tacotron2",   // one of the model in models/    
     "grad_clip": 0.02,      // upper limit for gradients for clipping.

layers/losses.py

@@ -23,6 +23,7 @@ class L1LossMasked(nn.Module):
             loss: An average loss value masked by the length.
         """
         # mask: (batch, max_len, 1)
+        target.requires_grad = False
         mask = sequence_mask(
             sequence_length=length, max_len=target.size(1)).unsqueeze(2).float()
         mask = mask.expand_as(input)
@@ -51,6 +52,7 @@ class MSELossMasked(nn.Module):
             loss: An average loss value masked by the length.
         """
         # mask: (batch, max_len, 1)
+        target.requires_grad = False
         mask = sequence_mask(
             sequence_length=length, max_len=target.size(1)).unsqueeze(2).float()
         mask = mask.expand_as(input)