training error about deep-fluids

[byungsook]

would you give me more information? I haven't tested this repo with TF 1.14. Try 1.12.

[Nimava]

Thanks so much. What information do you need? When I run the main.py, I have these messages:

Traceback (most recent call last):
  File "main.py", line 7, in <module>
    from trainer import Trainer
  File "/home/symphony/manta/trainer.py", line 9, in <module>
    from model import *
  File "/home/symphony/manta/model.py", line 3, in <module>
    from ops import *
  File "/home/symphony/manta/ops.py", line 6, in <module>
    import tensorflow.contrib.slim as slim
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow/contrib/__init__.py", line 37, in <module>
    from tensorflow.contrib import cudnn_rnn
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow/contrib/cudnn_rnn/__init__.py", line 38, in <module>
    from tensorflow.contrib.cudnn_rnn.python.layers import *
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow/contrib/cudnn_rnn/python/layers/__init__.py", line 23, in <module>
    from tensorflow.contrib.cudnn_rnn.python.layers.cudnn_rnn import *
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow/contrib/cudnn_rnn/python/layers/cudnn_rnn.py", line 20, in <module>
    from tensorflow.contrib.cudnn_rnn.python.ops import cudnn_rnn_ops
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow/contrib/cudnn_rnn/python/ops/cudnn_rnn_ops.py", line 22, in <module>
    from tensorflow.contrib.rnn.python.ops import lstm_ops
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow/contrib/rnn/__init__.py", line 91, in <module>
    from tensorflow.contrib.rnn.python.ops.lstm_ops import *
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow/contrib/rnn/python/ops/lstm_ops.py", line 298, in <module>
    @ops.RegisterGradient("BlockLSTM")
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 2489, in __call__
    _gradient_registry.register(f, self._op_type)
  File "/home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/registry.py", line 61, in register
    (self._name, name, function_name, filename, line_number))
KeyError: "Registering two gradient with name 'BlockLSTM'! (Previous registration was in register /home/symphony/.conda/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/registry.py:66)"

[byungsook]

It seems that there is a problem with importing slim. It didn't happen with TF 1.12, so I would recommend to try with different version of TF in your setting.

[Nimava]

Dear Kim, Thanks so much. OK, I'll try. Sorry for emailing. Github suspended my account because I live in Iran. Sincerely, Nima

…

On Tue, Oct 15, 2019 at 6:55 PM Byungsoo Kim ***@***.***> wrote: It seems that there is a problem with importing slim. It didn't happen with TF 1.12, so I would recommend to try with different version of TF in your setting. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#3?email_source=notifications&email_token=ANJ6GQYLSPFUG45RODBY7ITQOXOHXA5CNFSM4I72W63KYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEBJF36Y#issuecomment-542268923>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ANJ6GQ7FELZVN3DJ3KRZGZTQOXOHXANCNFSM4I72W63A> .