In [1]:

    

%matplotlib inline 
import tensorflow as tf 
import numpy as np 
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
import prettytensor as pt


    

In [2]:

    

from tensorflow.examples.tutorials.mnist import input_data
dataset = input_data.read_data_sets("data/MNIST/", one_hot=True)


    

    




Extracting data/MNIST/train-images-idx3-ubyte.gz
Extracting data/MNIST/train-labels-idx1-ubyte.gz
Extracting data/MNIST/t10k-images-idx3-ubyte.gz
Extracting data/MNIST/t10k-labels-idx1-ubyte.gz

In [3]:

    

image_size = 28
image_shape = (image_size, image_size)
image_flat = image_size*image_size
num_class = 10


    

In [4]:

    

layer1_filter_size = 5
layer1_input_channel = 1
layer1_output_channel = 16


layer2_filter_size = 5
layer2_output_channel = 36

num_output_fc1 = 128
num_output_fc2 = 10


    

In [5]:

    

x = tf.placeholder(tf.float32, [None, image_flat])


    

In [6]:

    

y = tf.placeholder(tf.float32, [None, num_class])


    

In [7]:

    

y_true_class = tf.argmax(y, dimension=1)


    

In [8]:

    

x_image = tf.reshape(x, [-1, image_size, image_size, layer1_input_channel])


    

In [11]:

    

x_pretty = pt.wrap(x_image)


    

In [15]:

    

with pt.defaults_scope(activation_fn = tf.nn.relu):
    y_pred, loss = x_pretty.\
                   conv2d(kernel = 5, depth = 16, name="layer_conv1").\
                   max_pool(kernel=2, stride=2)./
                   conv2d(kernel=5, depth = 36, name = "layer_conv2").\
                   max_pool(kernel=2, stride=2)./
                   flatten().\
                   fully_connected(size=128, name='layer_fc1').\
                    softmax_classifier(num_classes=num_classes, labels=y_true)


    

    




  File "<ipython-input-15-c454c52359dc>", line 2
    y_pred, loss = x_pretty.                   conv2d(kernel = 5, depth = 16, name="layer_conv1").                   max_pool(kernel=2, stride=2)./
                                                                                                                                                  ^
SyntaxError: invalid syntax

In [ ]: