UnboundLocalError: local variable 'class_name' referenced before assignment - theano

Question

I am new to Keras and Theano, and now trying to implement my own loss function on Keras. But this error showed up. I thought the problem lies in my own loss function, but I have now idea how to fix it. Could someone help me figure this out?
import theano
import theano.tensor as T
def cost_estimation(y_true, y_pred):
for k in range(10):
d=T.log(1+T.exp((int(bool(y_true[k]==min(y_true)))*2-1)*(y_pred[k]-y_true[k])))
cost=cost+d
return d
The keras layers:
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='relu'))
#loss=keras.losses.categorical_crossentropy,
model.compile(loss='cost_estimation',
optimizer='adam',
metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs,
verbose=1, validation_data=(x_test, y_test))
Here is the error:
---------------------------------------------------------------------------
UnboundLocalError Traceback (most recent call last)
<ipython-input-6-d63101c47c94> in <module>()
130 model.compile(loss='cost_estimation',
131 optimizer='adam',
--> 132 metrics=['accuracy'])
133
134 model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs,
/usr/local/lib/python2.7/dist-packages/keras/models.pyc in compile(self, optimizer, loss, metrics, sample_weight_mode, **kwargs)
764 metrics=metrics,
765 sample_weight_mode=sample_weight_mode,
--> 766 **kwargs)
767 self.optimizer = self.model.optimizer
768 self.loss = self.model.loss
/usr/local/lib/python2.7/dist-packages/keras/engine/training.pyc in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, **kwargs)
738 loss_functions = [losses.get(l) for l in loss]
739 else:
--> 740 loss_function = losses.get(loss)
741 loss_functions = [loss_function for _ in range(len(self.outputs))]
742 self.loss_functions = loss_functions
/usr/local/lib/python2.7/dist-packages/keras/losses.pyc in get(identifier)
88 if isinstance(identifier, six.string_types):
89 identifier = str(identifier)
---> 90 return deserialize(identifier)
91 elif callable(identifier):
92 return identifier
/usr/local/lib/python2.7/dist-packages/keras/losses.pyc in deserialize(name, custom_objects)
80 module_objects=globals(),
81 custom_objects=custom_objects,
---> 82 printable_module_name='loss function')
83
84
/usr/local/lib/python2.7/dist-packages/keras/utils/generic_utils.pyc in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
155 if fn is None:
156 raise ValueError('Unknown ' + printable_module_name,
--> 157 ':' + class_name)
158 return fn
159 else:
UnboundLocalError: local variable 'class_name' referenced before assignment

Answer 1

This seems to be an issue in keras codebase. It seems that if the a string is passed to the loss parameter this error arises. To fix this, pass
cost_estimation itself to loss, this way you avoid that branch of code.
model.compile(optimizer='rmsprop',
loss=cost_estimation, # not 'cost_estimation'
metrics=['accuracy'])