why make dict to self.__class__

[ghost]

    def __setattr__(self, name, value):
        if isinstance(value, (list, tuple)):
            value = [self.__class__(x)
                     if isinstance(x, dict) else x for x in value]
        elif isinstance(value, dict) and not isinstance(value, self.__class__):
            value = self.__class__(value)
        super(EasyDict, self).__setattr__(name, value)
        super(EasyDict, self).__setitem__(name, value)

I want to know why make dict to easydict.
I use the type dict of value , then this value can not use multiple gpu.

[ghost]

def scatter(inputs, target_gpus, dim=0):

    def scatter_map(obj):
        if isinstance(obj, torch.Tensor):
            return Scatter.apply(target_gpus, None, dim, obj)
        if isinstance(obj, tuple) and len(obj) > 0:
            return list(zip(*map(scatter_map, obj)))
        if isinstance(obj, list) and len(obj) > 0:
            return list(map(list, zip(*map(scatter_map, obj))))
        if isinstance(obj, dict) and len(obj) > 0:
            return list(map(type(obj), zip(*map(scatter_map, obj.items()))))
        return [obj for targets in target_gpus]


    try:
        res = scatter_map(inputs)
    finally:
        scatter_map = None
    return res

from easydict import EasyDict as edict
batch = edict()
a = dict({"st":[12, 29,  5,  8]})
batch["ts_label"] = a
target_gpus = [0,1]
print(type(batch["ts_label"])) # easydict not dict 
output = scatter(batch["ts_label"],target_gpus)
print(output)

  File "/home/ll/anaconda3/envs/py27_torch/lib/python2.7/site-packages/easydict/__init__.py", line 117, in __init__
    for k, v in d.items():
AttributeError: 'tuple' object has no attribute 'items'

the function scatter is from torch.nn.data_parallel.py