def __init__(self, gan, config):
    """
    Initializes a gan component based on a `gan` and a `config` dictionary.
    Different components require different config variables.  
    A `ValidationException` is raised if the GAN component configuration fails to validate.
    """
    self.gan = gan
    self.config = hc.Config(config)
    errors = self.validate()
    if errors != []:
        raise ValidationException(self.__class__.__name__+": " +"\n".join(errors))
    self.create_ops(config)

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

def build(self, net):
    gan = self.gan
    ops = self.ops
    config = self.config
    activation = ops.lookup(config.activation or 'lrelu')
    print("[dcgan] NET IS", net)
    net = ops.linear(net, 1024)
    shape = ops.shape(net)
    x_shape = ops.shape(self.gan.inputs.x)
    output_size = x_shape[1]*x_shape[2]*x_shape[3]
    print("Output size", output_size)
    net = activation(net)
    net = ops.linear(net, 2*1024)
    net = activation(net)
    net = ops.linear(net, output_size)
    net = ops.lookup('tanh')(net)
    net = ops.reshape(net, output_size)
    self.sample = net
    return self.sample

def create(self, sample=None):
    gan = self.gan
    ops = self.ops
    if sample is None:
        sample = gan.encoder.sample
    return self.build(sample)

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 layer_filter(self, net):
    ops = self.ops
    gan = self.gan
    config = self.config
    if config.layer_filter:
        print("[base generator] applying layer filter", config['layer_filter'])
        fltr = config.layer_filter(gan, self.config, net)
        if fltr is not None:
            net = ops.concat(axis=3, values=[net, fltr])
    return net

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 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 []

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

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