model.compile(loss='mean_squared_error', optimizer='sgd')

from keras import losses
model.compile(loss=losses.mean_squared_error, optimizer='sgd')

def mean_squared_error(y_true, y_pred):
    return K.mean(K.square(y_pred - y_true), axis=-1)

def mean_absolute_error(y_true, y_pred):
    return K.mean(K.abs(y_pred - y_true), axis=-1)

def mean_absolute_percentage_error(y_true, y_pred):
    diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true),
                                            K.epsilon(),
                                            None))
    return 100. * K.mean(diff, axis=-1)

def mean_squared_logarithmic_error(y_true, y_pred):
    first_log = K.log(K.clip(y_pred, K.epsilon(), None) + 1.)
    second_log = K.log(K.clip(y_true, K.epsilon(), None) + 1.)
    return K.mean(K.square(first_log - second_log), axis=-1)

def squared_hinge(y_true, y_pred):
    return K.mean(K.square(K.maximum(1. - y_true * y_pred, 0.)), axis=-1)

def hinge(y_true, y_pred):
    return K.mean(K.maximum(1. - y_true * y_pred, 0.), axis=-1)

def categorical_hinge(y_true, y_pred):
    pos = K.sum(y_true * y_pred, axis=-1)
    neg = K.max((1. - y_true) * y_pred, axis=-1)
    return K.maximum(0., neg - pos + 1.)

def logcosh(y_true, y_pred):
    """Logarithm of the hyperbolic cosine of the prediction error.
    `log(cosh(x))` is approximately equal to `(x ** 2) / 2` for small `x` and
    to `abs(x) - log(2)` for large `x`. This means that 'logcosh' works mostly
    like the mean squared error, but will not be so strongly affected by the
    occasional wildly incorrect prediction.
    # Arguments
        y_true: tensor of true targets.
        y_pred: tensor of predicted targets.
    # Returns
        Tensor with one scalar loss entry per sample.
    """
    def _logcosh(x):
        return x + K.softplus(-2. * x) - K.log(2.)
    return K.mean(_logcosh(y_pred - y_true), axis=-1)

def categorical_crossentropy(y_true, y_pred):
    return K.categorical_crossentropy(y_true, y_pred)

from keras.utils.np_utils import to_categorical
categorical_labels = to_categorical(int_labels, num_classes=None)

def sparse_categorical_crossentropy(y_true, y_pred):
    return K.sparse_categorical_crossentropy(y_true, y_pred)
def sparse_categorical_crossentropy(target, output, from_logits=False):
    """Categorical crossentropy with integer targets.

    # Arguments
        target: An integer tensor.
        output: A tensor resulting from a softmax
            (unless `from_logits` is True, in which
            case `output` is expected to be the logits).
        from_logits: Boolean, whether `output` is the
            result of a softmax, or is a tensor of logits.

    # Returns
        Output tensor.
    """
    # Note: tf.nn.sparse_softmax_cross_entropy_with_logits
    # expects logits, Keras expects probabilities.
    if not from_logits:
        _epsilon = _to_tensor(epsilon(), output.dtype.base_dtype)
        output = tf.clip_by_value(output, _epsilon, 1 - _epsilon)
        output = tf.log(output)

    output_shape = output.get_shape()
    targets = cast(flatten(target), 'int64')
    logits = tf.reshape(output, [-1, int(output_shape[-1])])
    res = tf.nn.sparse_softmax_cross_entropy_with_logits(
        labels=targets,
        logits=logits)
    if len(output_shape) >= 3:
        # if our output includes timestep dimension
        # or spatial dimensions we need to reshape
        return tf.reshape(res, tf.shape(output)[:-1])
    else:
        return res

def binary_crossentropy(y_true, y_pred):
    return K.mean(K.binary_crossentropy(y_true, y_pred), axis=-1)
def binary_crossentropy(target, output, from_logits=False):
    """Binary crossentropy between an output tensor and a target tensor.

    # Arguments
        target: A tensor with the same shape as `output`.
        output: A tensor.
        from_logits: Whether `output` is expected to be a logits tensor.
            By default, we consider that `output`
            encodes a probability distribution.

    # Returns
        A tensor.
    """
    # Note: tf.nn.sigmoid_cross_entropy_with_logits
    # expects logits, Keras expects probabilities.
    if not from_logits:
        # transform back to logits
        _epsilon = _to_tensor(epsilon(), output.dtype.base_dtype)
        output = tf.clip_by_value(output, _epsilon, 1 - _epsilon)
        output = tf.log(output / (1 - output))

    return tf.nn.sigmoid_cross_entropy_with_logits(labels=target,logits=output)

def kullback_leibler_divergence(y_true, y_pred):
    y_true = K.clip(y_true, K.epsilon(), 1)
    y_pred = K.clip(y_pred, K.epsilon(), 1)
    return K.sum(y_true * K.log(y_true / y_pred), axis=-1)

def poisson(y_true, y_pred):
    return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)

def cosine_proximity(y_true, y_pred):
    y_true = K.l2_normalize(y_true, axis=-1)
    y_pred = K.l2_normalize(y_pred, axis=-1)
    return -K.sum(y_true * y_pred, axis=-1)