-
### Environment info
Operating System: Ubuntu 14.04 64bit
Actually it is a docker env
nvidia/cuda:7.5-cudnn4-devel
Installed version of CUDA and cuDNN: CUDA7.5 and cuDNN4
(please attach the output o…
-
Code:
1. import tensorflow as tf
2. import tensorlayer as tl
3. import numpy as np
4. from PIL import Image
5. import os
6.
7.
8. def _int64_feature(value):
9. return tf.train.Feature…
ghost updated
7 years ago
-
When using the `paddle.v2` API, it threw a Fatal Python error:
```python
$ python
Python 2.7.13 (default, Dec 18 2016, 07:03:39)
[GCC 4.2.1 Compatible Apple LLVM 8.0.0 (clang-800.0.42.1)] on da…
-
Assuming I want to batch series of inputs and propagate the cell state from one session run towards another for an epoch:
```
for batch in epoch:
state = initial_state.eval()
feed_dict = {initial…
-
### Environment info
Operating System:
Mac OS X 10.11.4
Tensorflow installed from pre-built pip (no CUDA):
0.10.0rc0
### Problem
I have problems with restoring my net [(from SO)](http://stackoverflo…
kalle updated
8 years ago
-
Thanks for your debug, but...
1. "max_length = tf.shape(**self.outputs**)[1]
self.outputs = tf.reshape(tf.concat(1, outputs), [-1, max_length, n_hidden])", this is your new code
but also …