ZeroDivisionError while training wavenet

[caixxiong]

the traceback info is following: Traceback (most recent call last): File "train.py", line 140, in main() File "train.py", line 132, in main wavenet_train(args, log_dir, hparams, args.wavenet_input) File "/home/caixiong/Tacotron-2/wavenet_vocoder/train.py", line 346, in wavenet_train return train(log_dir, args, hparams, input_path) File "/home/caixiong/Tacotron-2/wavenet_vocoder/train.py", line 230, in train model, stats = model_train_mode(args, feeder, hparams, global_step) File "/home/caixiong/Tacotron-2/wavenet_vocoder/train.py", line 173, in model_train_mode model = create_model(model_name or args.model, hparams, init) File "/home/caixiong/Tacotron-2/wavenet_vocoder/models/init.py", line 16, in create_model return WaveNet(hparams, init) File "/home/caixiong/Tacotron-2/wavenet_vocoder/models/wavenet.py", line 186, in init up_layers=len(hparams.upsample_scales), name='SubPixelConvolutionlayer{}'.format(i)) File "/home/caixiong/Tacotron-2/wavenet_vocoder/models/modules.py", line 537, in init init_kernel = tf.constant_initializer(self._init_kernel(kernel_size, strides, conv_filters), dtype=tf.float32) if NN_init else None File "/home/caixiong/Tacotron-2/wavenet_vocoder/models/modules.py", line 634, in _init_kernel init_kernel[i, j_i] = 1. / overlap if kernel_size[1] % 2 == 0 else 1. ZeroDivisionError: float division by zero