在將自定義的網路權重載入到網路中時，報錯：

AttributeError: 'dict' object has no attribute 'seek'. You can only torch.load from a file that is seekable. Please pre-load the data into a buffer like io.BytesIO and try to load from it instead.

我們一步一步分析。

模型網路權重儲存額程式碼是：torch.save(net.state_dict(),'net.pkl')

（1）檢視獲取模型權重的原始碼：

pytorch原始碼：net.state_dict()

def state_dict(self,destination=None,prefix='',keep_vars=False):
  r"""Returns a dictionary containing a whole state of the module.

  Both parameters and persistent buffers (e.g. running averages) are
  included. Keys are corresponding parameter and buffer names.

  Returns:
    dict:
      a dictionary containing a whole state of the module

  Example::

    >>> module.state_dict().keys()
    ['bias','weight']

  """

將網路中所有的狀態儲存到一個字典中了，我自己構建的就是一個字典，沒問題！

（2）檢視儲存模型權重的原始碼:

pytorch原始碼：torch.save()

def save(obj,f,pickle_module=pickle,pickle_protocol=DEFAULT_PROTOCOL):
  """Saves an object to a disk file.

  See also: :ref:`recommend-saving-models`

  Args:
    obj: saved object
    f: a file-like object (has to implement write and flush) or a string
      containing a file name
    pickle_module: module used for pickling metadata and objects
    pickle_protocol: can be specified to override the default protocol

  .. warning::
    If you are using Python 2,torch.save does NOT support StringIO.StringIO
    as a valid file-like object. This is because the write method should return
    the number of bytes written; StringIO.write() does not do this.

    Please use something like io.BytesIO instead.

函式功能是將字典儲存為磁碟檔案（二進位制資料），那麼我們在torch.load（）時，就是在記憶體中載入二進位制資料，這就是報錯點。

解決方案：將字典儲存為BytesIO檔案之後，模型再net.load_state_dict()

#b為自定義的字典
torch.save(b,'new.pkl')
net.load_state_dict(torch.load(b))

解決方法很簡單，主要記錄解決思路。

以上這篇pytorch載入自定義網路權重的實現就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支援我們。