I'm approaching to the world of deep learning, and the framework that I'm using is Tensorflow. In order to start quickly, I've seen that there are high level API called TFLearn, which makes the creation of a network a lot easier. Unfortunately, there are no working examples. In particular, I'm trying this example:
but it can't find the layers. I've tried to import tflearn in this way:
import tensorflow.contrib.learn as tflearn
and the dataset in this way
import tensorflow.contrib.learn.python.learn.datasets.mnist as mnist
and they works, but I'm still not able to use the layers.
EDIT
I also tried to import in this way (as reported on tflearn github page):
import tensorflow.contrib.learn.python.learn as tflearn
and I get this error:
AttributeError: module 'tensorflow.contrib.learn.python.learn' has no attribute 'conv_2d'
What can I do?
Don't use
import tensorflow.contrib.learn as tflearn
Instead install tflearn in your terminal, using installation guide http://tflearn.org/installation/
Then, import like:
import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.estimator import regression
This way you can use the layers.