In [1]:

    

!sudo unlink /usr/local/cuda
!sudo ln -s /usr/local/cuda-7.5 /usr/local/cuda


    

In [2]:

    

import tensorflow as tf
import numpy as np


    

In [3]:

    

NUM_CORES = 6

config = tf.ConfigProto(
    inter_op_parallelism_threads=NUM_CORES,
    intra_op_parallelism_threads=NUM_CORES
)


    

In [4]:

    

# Creating the placeholders. Note that we include names for more informative errors
# and shapes as tensorflow will do static size checking.
x_0 = tf.placeholder(tf.float32, shape=(1, 10), name='x_0')
W_0 = tf.placeholder(tf.float32, shape=(10, 4), name='W_0')
b_0 = tf.placeholder(tf.float32, shape=(1,  4), name='b_0')


    

In [5]:

    

# The fan-in to the summing junction and the summing operation.
y_0 = tf.matmul(x_0, W_0) + b_0


    

In [6]:

    

# The activation function
a_0 = tf.nn.sigmoid(y_0)


    

In [7]:

    

# Now for the second layer.
# x_1 = tf.placeholder(tf.float32, shape=(1, 4), name='x_1')
W_1 = tf.placeholder(tf.float32, shape=(4, 2), name='W_1')
b_1 = tf.placeholder(tf.float32, shape=(1, 2), name='b_1')


    

In [8]:

    

# The fan-in to the summing junction and the summing operation.
y_1 = tf.matmul(a_0, W_1) + b_1


    

In [9]:

    

# The activation function
a_1 = tf.nn.sigmoid(y_1)


    

In [10]:

    

# Adding a softmax filter
m = tf.nn.softmax(a_1)


    

In [11]:

    

# The activation function doesn't really change here
with tf.Session(config=config) as s:
    s.run(tf.initialize_all_variables())
    
    # Let's create some numpy matrices.
    # This is for a single layer of four neurons
    W_0_in = np.random.rand(10, 4)
    x_0_in = np.random.rand(1, 10)
    b_0_in = np.random.rand(1,  4)
    W_1_in = np.random.rand(4,  2)
    b_1_in = np.random.rand(1,  2)
    
    val = s.run(m,
        feed_dict={
            x_0: x_0_in,
            W_0: W_0_in,
            b_0: b_0_in,
            W_1: W_1_in,
            b_1: b_1_in
        })
    
    print val


    

    




[[ 0.50247377  0.49752623]]

In [ ]: