def __init__(self, config=None, inputs=None, device='/gpu:0', ops_config=None, ops_backend=TensorflowOps,
        batch_size=None, width=None, height=None, channels=None):
    """ Initialized a new GAN."""
    self.inputs = inputs
    self.device = device
    self.ops_backend = ops_backend
    self.ops_config = ops_config
    self.created = False
    self.components = []
    self._batch_size = batch_size
    self._width = width
    self._height = height
    self._channels = channels
    if config == None:
        config = hg.Configuration.default()
    # A GAN as a component has a parent of itself
    # gan.gan.gan.gan.gan.gan
    GANComponent.__init__(self, self, config)

def batch_size(self):
    if self._batch_size:
        return self._batch_size
    if self.inputs == None:
        raise ValidationException("gan.batch_size() requested but no inputs provided")
    return self.ops.shape(self.inputs.x)[0]

def biases(self):
    """
        Biases of the GAN component.
    """
    return self.ops.biases

def channels(self):
    if self._channels:
        return self._channels
    if self.inputs == None:
        raise ValidationException("gan.channels() requested but no inputs provided")
    return self.ops.shape(self.inputs.x)[-1]

def create(self):
    if self.created:
        raise ValidationException("gan.create already called. Cowardly refusing to create graph twice")
    self.created = True

def create_component(self, defn, *args, **kw_args):
    if defn == None:
        return None
    if defn['class'] == None:
        raise ValidationException("Component definition is missing '" + name + "'")
    gan_component = defn['class'](self, defn, *args, **kw_args)
    self.components.append(gan_component)
    return gan_component

def create_ops(self, config):
    """
    Create the ops object as `self.ops`.  Also looks up config
    """
    if self.gan is None:
        return
    if self.gan.ops_backend is None:
        return
    self.ops = self.gan.ops_backend(config=self.config, device=self.gan.device)
    self.config = self.gan.ops.lookup(config)

def fully_connected_from_list(self, nets):
    results = []
    ops = self.ops
    for net, net2 in nets:
        net = ops.concat([net, net2], axis=3)
        shape = ops.shape(net)
        bs = shape[0]
        net = ops.reshape(net, [bs, -1])
        features = ops.shape(net)[1]
        net = ops.linear(net, features)
        #net = self.layer_regularizer(net)
        net = ops.lookup('lrelu')(net)
        #net = ops.linear(net, features)
        net = ops.reshape(net, shape)
        results.append(net)
    return results

def get_config_value(self, symbol):
    if symbol in self.config:
        config = hc.Config(hc.lookup_functions(self.config[symbol]))
        return config
    return None

def height(self):
    if self._height:
        return self._height
    if self.inputs == None:
        raise ValidationException("gan.height() requested but no inputs provided")
    return self.ops.shape(self.inputs.x)[1]

def layer_regularizer(self, net):
    symbol = self.config.layer_regularizer
    op = self.gan.ops.lookup(symbol)
    if op:
        net = op(self, net)
    return net

def load(self, save_file):
    save_file = os.path.expanduser(save_file)
    if os.path.isfile(save_file) or os.path.isfile(save_file + ".index" ):
        print("[hypergan] |= Loading network from "+ save_file)
        dir = os.path.dirname(save_file)
        print("[hypergan] |= Loading checkpoint from "+ dir)
        ckpt = tf.train.get_checkpoint_state(os.path.expanduser(dir))
        if ckpt and ckpt.model_checkpoint_path:
            saver = tf.train.Saver()
            saver.restore(self.session, save_file)
            loadedFromSave = True
            return True
        else:
            return False
    else:
        return False

def permute(self, nets, k):
    return list(itertools.permutations(nets, k))

def relation_layer(self, net):
    ops = self.ops
    #hack
    shape = ops.shape(net)
    input_size = shape[1]*shape[2]*shape[3]
    netlist = self.split_by_width_height(net)
    permutations = self.permute(netlist, 2)
    permutations = self.fully_connected_from_list(permutations)
    net = ops.concat(permutations, axis=3)
    #hack
    bs = ops.shape(net)[0]
    net = ops.reshape(net, [bs, -1])
    net = ops.linear(net, input_size)
    net = ops.reshape(net, shape)
    return net

def required(self):
    """
    Return a list of required config strings and a `ValidationException` will be thrown if any are missing.
    Example: 
    ```python
        class MyComponent(GANComponent):
            def required(self):
                "learn rate is required"
                ["learn_rate"]
    ```
    """
    return []

def reuse(self, net):
    self.ops.reuse()
    net = self.build(net)
    self.ops.stop_reuse()
    return net

def save(self, save_file):
    print("[hypergan] Saving network to ", save_file)
    os.makedirs(os.path.expanduser(os.path.dirname(save_file)), exist_ok=True)
    saver = tf.train.Saver()
    saver.save(self.session, save_file)

def split_batch(self, net, count=2):
    """ 
    Discriminators return stacked results (on axis 0).  
    
    This splits the results.  Returns [d_real, d_fake]
    """
    ops = self.ops or self.gan.ops
    s = ops.shape(net)
    bs = s[0]
    nets = []
    net = ops.reshape(net, [bs, -1])
    start = [0 for x in ops.shape(net)]
    for i in range(count):
        size = [bs//count] + [x for x in ops.shape(net)[1:]]
        nets.append(ops.slice(net, start, size))
        start[0] += bs//count
    return nets

def split_by_width_height(self, net):
    elems = []
    ops = self.gan.ops
    shape = ops.shape(net)
    bs = shape[0]
    height = shape[1]
    width = shape[2]
    for i in range(width):
        for j in range(height):
            elems.append(ops.slice(net, [0, i, j, 0], [bs, 1, 1, -1]))
    return elems

def validate(self):
    """
    Validates a GANComponent.  Return an array of error messages. Empty array `[]` means success.
    """
    errors = []
    required = self.required()
    for argument in required:
        if(self.config.__getattr__(argument) == None):
            errors.append("`"+argument+"` required")
    if(self.gan is None):
        errors.append("GANComponent constructed without GAN")
    return errors

def variables(self):
    """
        All variables associated with this component.
    """
    return self.ops.variables()

def weights(self):
    """
        The weights of the GAN component.
    """
    return self.ops.weights

def width(self):
    if self._width:
        return self._width
    if self.inputs == None:
        raise ValidationException("gan.width() requested but no inputs provided")
    return self.ops.shape(self.inputs.x)[2]