Problem with training

[jayajackson]

I had tried to train the R-net model ,but... I get the following error...

"Training...Traceback (most recent call last):
File "train.py", line 80, in
ModelCheckpoint(path, verbose=1, save_best_only=True)
File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 87, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1725, in fit_generator
self._make_train_function()
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 937, in _make_train_function
self.total_loss)
File "/usr/local/lib/python2.7/dist-packages/keras/optimizers.py", line 335, in get_updates
grads = self.get_gradients(loss, params)
File "/usr/local/lib/python2.7/dist-packages/keras/optimizers.py", line 71, in get_gradients
grads = K.gradients(loss, params)
File "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py", line 1210, in gradients
return T.grad(loss, variables)
File "/usr/local/lib/python2.7/dist-packages/theano/gradient.py", line 589, in grad
handle_disconnected(elem)
File "/usr/local/lib/python2.7/dist-packages/theano/gradient.py", line 576, in handle_disconnected
raise DisconnectedInputError(message)
theano.gradient.DisconnectedInputError:
Backtrace when that variable is created:

File "train.py", line 40, in
model = RNet(hdim=args.hdim, dropout_rate=args.dropout, N=None, M=None)
File "/home/lab/Desktop/project/R-NET-in-Keras-master/model.py", line 50, in init
WP_u = SharedWeight(size=(H, 1), name='WP_u')
File "/home/lab/Desktop/project/R-NET-in-Keras-master/SharedWeight.py", line 66, in SharedWeight
input_layer = SharedWeightLayer(**kwargs)
File "/home/lab/Desktop/project/R-NET-in-Keras-master/SharedWeight.py", line 30, in init
regularizer=self.regularizer)
File "/usr/local/lib/python2.7/dist-packages/keras/legacy/interfaces.py", line 87, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 391, in add_weight
weight = K.variable(initializer(shape), dtype=dtype, name=name)
File "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py", line 148, in variable
strict=False)"

What should I do to fix it?
Thank You