Cannot train: 'tuple' object has no attribute 'eval' about word-rnn-tensorflow HOT 8 CLOSED

I made a PR but using sess.run(x) instead of convert_to_tensor and then eval. I tested it on two machines one with standard installation and one with CUDA installation (the one with the original issue).

from word-rnn-tensorflow.

I got exactly the same problem with Python 2.7. I think the problem comes from initial_tuple which is organized as a tuple. Previously it is not a tuple.

from word-rnn-tensorflow.

Thanks! Do you know which version of TF did you use?

On Fri, Sep 2, 2016 at 7:35 AM, moonlightlane [email protected]
wrote:

I got exactly the same problem with Python 2.7. I think the problem comes
from initial_tuple which is organized as a tuple. Previously it is not a
tuple.

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
#9 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AA3DV4S8kxLDQcDSE4tSMp-8__KUfFC5ks5ql2FJgaJpZM4Jq9_O
.

from word-rnn-tensorflow.

I think it is 0.10. There are some posts on github about this issue but none of them work for me... model.initial_state looks like this: (LSTMStateTuple(c=<tf.Tensor 'zeros:0' shape=(50, 128) dtype=float32>, h=<tf.Tensor 'zeros_1:0' shape=(50, 128) dtype=float32>), LSTMStateTuple(c=<tf.Tensor 'zeros_2:0' shape=(50, 128) dtype=float32>, h=<tf.Tensor 'zeros_3:0' shape=(50, 128) dtype=float32>)) , and it seems that the state is a tuple of tuples. I don't yet have a good idea how to deal with it.

from word-rnn-tensorflow.

Let me try with 0.10. Thanks!

On Fri, Sep 2, 2016 at 7:56 AM, moonlightlane [email protected]
wrote:

I think it is 0.10. There are some posts on github about this issue but
none of them work for me... model.initial_state looks like this: (LSTMStateTuple(c=<tf.Tensor
'zeros:0' shape=(50, 128) dtype=float32>, h=<tf.Tensor 'zeros_1:0'
shape=(50, 128) dtype=float32>), LSTMStateTuple(c=<tf.Tensor 'zeros_2:0'
shape=(50, 128) dtype=float32>, h=<tf.Tensor 'zeros_3:0' shape=(50, 128)
dtype=float32>))
, and it seems that the state is a tuple of tuples. I don't yet have a
good idea how to deal with it.

—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
#9 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AA3DV5LOM5ZpOeXgAPXs3XffQRIOibKTks5ql2Y2gaJpZM4Jq9_O
.

from word-rnn-tensorflow.

I am using Ubuntu/Linux 64-bit CPU Only, Python 2.7 Tensorflow-0.11 and the work around in the issue below fixed this issue for me
sherjilozair/char-rnn-tensorflow#47

TL;DR
in train.py try replacing the line
state = model.initial_state.eval()
with
model.initial_state = tf.convert_to_tensor(model.initial_state) state = model.initial_state.eval()

from word-rnn-tensorflow.

Can you write a pull request for us?

Sung

On Wed, Oct 5, 2016 at 11:14 AM, astr010 [email protected] wrote:

I am using Ubuntu/Linux 64-bit CPU Only, Python 2.7 Tensorflow-0.11 and
the work around in the issue below fixed this issue for me
sherjilozair/char-rnn-tensorflow#47
sherjilozair/char-rnn-tensorflow#47

TL;DR
in train.py try replacing the line
state = model.initial_state.eval()
with
model.initial_state = tf.convert_to_tensor(model.initial_state) state =
model.initial_state.eval()

—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
#9 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AA3DV02yQDz4ftd3YTjC3ij3k8_w3a2yks5qwxX5gaJpZM4Jq9_O
.

from word-rnn-tensorflow.

Please reopen if this issue reoccurs.

from word-rnn-tensorflow.