AttributeError: 'Graph' object has no attribute 'y'

[Oakford]

Using the latest version, the program "eval.py" throws an error

Traceback (most recent call last):
  File "eval.py", line 70, in <module>
    eval()
  File "eval.py", line 26, in eval
    g = Graph(is_training=False)
  File "tacotron\train.py", line 35, in __init__
    self.decoder_inputs = shift_by_one(self.y)
AttributeError: 'Graph' object has no attribute 'y'

[bakercp]

I am getting the same issue. I trained using

python train_multi_gpus.py

My hyperparmaters.py was modified slightly for 2 x GPUs and more epochs:

diff --git a/hyperparams.py b/hyperparams.py
index 5aaccab..8ac9032 100644
--- a/hyperparams.py
+++ b/hyperparams.py
@@ -35,13 +35,13 @@ class Hyperparams:
     # training scheme
     lr = 0.001 # Paper => Exponential decay
     logdir = "logdir"
-    batch_size = 32
-    num_epochs = 200 # Paper => 2M global steps!
+    batch_size = 64 
+    num_epochs = 2000 # Paper => 2M global steps!
     loss_type = "l1" # Or you can test "l2"
     num_samples = 32

     # etc
-    num_gpus = 1 # If you have multiple gpus, adjust this option, and increase the batch size
+    num_gpus = 2 # If you have multiple gpus, adjust this option, and increase the batch size
                  # and run `train_multiple_gpus.py` instead of `train.py`.
     target_zeros_masking = False # If True, we mask zero padding on the target, 
                                  # so exclude them from the loss calculation.     

[Kyubyong]

Sorry for this. I forgot to change self.decoder_inputs to self.y. Pull now.

[bakercp]

Fixed for me. Thanks!