In [1]:

    

import tensorflow as tf


    

In [2]:

    

# Output depth
k_output = 64


    

In [3]:

    

# Image Properties
image_width = 10
image_height = 10
color_channels = 3


    

In [4]:

    

# Convolution filter
filter_size_width = 5
filter_size_height = 5


    

In [5]:

    

# Input/Image
input = tf.placeholder(tf.float32,shape=[None, image_height, image_width, color_channels])


    

In [6]:

    

# Weight and bias
weight = tf.Variable(tf.truncated_normal(
    [filter_size_height, filter_size_width, color_channels, k_output]))
bias = tf.Variable(tf.zeros(k_output))


    

In [7]:

    

# Apply Convolution
conv_layer = tf.nn.conv2d(input, weight, strides=[1, 2, 2, 1], padding='SAME')


    

In [8]:

    

# Add bias
conv_layer = tf.nn.bias_add(conv_layer, bias)


    

In [9]:

    

# Apply activation function
conv_layer = tf.nn.relu(conv_layer)


    

In [10]:

    

# Apply Max Pooling
conv_layer = tf.nn.max_pool(
    conv_layer,
    ksize=[1, 2, 2, 1],
    strides=[1, 2, 2, 1],
    padding='SAME')


    

In [11]:

    

print(conv_layer)


    

    




Tensor("MaxPool:0", shape=(?, 3, 3, 64), dtype=float32)

In [ ]: