search

suriyadeepan / practical_seq2seq

A simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly
http://suriyadeepan.github.io/2016-12-31-practical-seq2seq/
GNU General Public License v3.0
570 stars 270 forks source link

Cannot load pretrained model: NotFoundError #59

Closed adamknaze closed 6 years ago

adamknaze commented 6 years ago

I've been trying hard to get the pretrainded model working, but i keep getting NotFoundError

`NotFoundError Traceback (most recent call last) c:\program files\python35\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, args) 1021 try: -> 1022 return fn(args) 1023 except errors.OpError as e:

c:\program files\python35\lib\site-packages\tensorflow\python\client\session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata) 1003 feed_dict, fetch_list, target_list, -> 1004 status, run_metadata) 1005

c:\program files\python35\lib\contextlib.py in exit(self, type, value, traceback) 65 try: ---> 66 next(self.gen) 67 except StopIteration:

c:\program files\python35\lib\site-packages\tensorflow\python\framework\errors_impl.py in raise_exception_on_not_ok_status() 468 compat.as_text(pywrap_tensorflow.TF_Message(status)), --> 469 pywrap_tensorflow.TF_GetCode(status)) 470 finally:

NotFoundError: Key decoder/embedding_rnn_seq2seq/embedding_rnn_decoder/rnn_decoder/multi_rnn_cell/cell_1/basic_lstm_cell/biases/Adam_1 not found in checkpoint [[Node: save/RestoreV2_13 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_13/tensor_names, save/RestoreV2_13/shape_and_slices)]] [[Node: save/RestoreV2_25/_1 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_201_save/RestoreV2_25", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]`

This happens on tensorflow 1.0.0, when i try to use version 0.12.0, i cannot even build the graph, and get module 'tensorflow.contrib.rnn' has no attribute 'core_rnn_cell' (and yes, i tried solution suggested here )

do you have any idea what might be the problem? thanks