How to use the batchflow.models.tf.resnet.ResNet function in batchflow

def default_config(cls):
        config = ResNet18.default_config()
        config['body/block/resnext'] = True
        return config


class ResNeXt34(ResNet):
    """ The ResNeXt-34 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet34.default_config()
        config['body/block/resnext'] = True
        return config


class ResNeXt50(ResNet):
    """ The ResNeXt-50 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet50.default_config()
        config['body/block/resnext'] = True
        return config


class ResNeXt101(ResNet):
    """ The ResNeXt-101 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet101.default_config()
        config['body/block/resnext'] = True
        return config

""" An ordinary ResNet block

        Parameters
        ----------
        inputs : tf.Tensor
            input tensor
        name : str
            scope name

        Returns
        -------
        tf.Tensor
        """
        kwargs = cls.fill_params('body/br', **kwargs)
        kwargs['filters'] = cls.num_channels(inputs, data_format=kwargs['data_format'])
        return ResNet.block(inputs, name=name, **kwargs)

config['body/num_blocks'] = [2, 2, 2, 2]
        config['body/block/bottleneck'] = None
        return config


class ResNet34(ResNet):
    """ The original ResNet-34 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet.default_config()
        config['body/num_blocks'] = [3, 4, 6, 3]
        config['body/block/bottleneck'] = None
        return config


class ResNet50(ResNet):
    """ The original ResNet-50 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet34.default_config()
        config['body/block/bottleneck'] = 4
        return config


class ResNet101(ResNet):
    """ The original ResNet-101 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet.default_config()
        config['body/num_blocks'] = [3, 4, 23, 3]
        config['body/block/bottleneck'] = 4
        return config

def trunk(cls, inputs, name='trunk', **kwargs):
        """ Trunk branch

        Parameters
        ----------
        inputs : tf.Tensor
            input tensor
        name : str
            scope name

        Returns
        -------
        tf.Tensor
        """
        kwargs = cls.fill_params('body/trunk', **kwargs)
        x = ResNet.double_block(inputs, name=name, **kwargs)
        return x

""" Two ResNet blocks of two 3x3 convolution + shortcut

        Parameters
        ----------
        inputs : tf.Tensor
            input tensor
        filters : int
            number of output filters
        name : str
            scope name

        Returns
        -------
        tf.Tensor
        """
        return ResNet.double_block(inputs, filters=filters, name=name, downsample=True, **kwargs)

""" Two ResNet blocks of two 3x3 convolution + shortcut

        Parameters
        ----------
        inputs : tf.Tensor
            input tensor
        filters : int
            number of output filters
        name : str
            scope name

        Returns
        -------
        tf.Tensor
        """
        return ResNet.double_block(inputs, filters=filters, name=name, downsample=True, **kwargs)

def default_config(cls):
        config = ResNet.default_config()
        config['body/num_blocks'] = [3, 8, 36, 3]
        config['body/block/bottleneck'] = True
        return config

"""
        num_blocks = cls.get('num_blocks', cls.fill_params('body', **kwargs))

        with tf.variable_scope(name):
            x = cls.body(inputs, name='body', **kwargs)

            scope = tf.get_default_graph().get_name_scope()
            encoder_tensors = []
            for i, _ in enumerate(num_blocks):
                tensor_name = scope + '/body/group-%d'%i + '/output:0'
                x = tf.get_default_graph().get_tensor_by_name(tensor_name)
                encoder_tensors.append(x)
        return encoder_tensors


class ResNet18(ResNet):
    """ The original ResNet-18 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet.default_config()
        config['body/num_blocks'] = [2, 2, 2, 2]
        config['body/block/bottleneck'] = False
        return config


class ResNet34(ResNet):
    """ The original ResNet-34 architecture """
    @classmethod
    def default_config(cls):
        config = ResNet.default_config()
        config['body/num_blocks'] = [3, 4, 6, 3]
        config['body/block/bottleneck'] = False