In [ ]:

    

# -*- coding: utf-8 -*-

""" Convolutional Neural Network for MNIST dataset classification task.
References:
    Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based
    learning applied to document recognition." Proceedings of the IEEE,
    86(11):2278-2324, November 1998.
Links:
    [MNIST Dataset] http://yann.lecun.com/exdb/mnist/
"""

from __future__ import division, print_function, absolute_import

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.normalization import local_response_normalization
from tflearn.layers.estimator import regression


    

In [ ]:

    

# Data loading and preprocessing
import tflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(data_dir='/tmp/mnist-data', one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])


    

In [ ]:

    

# Building convolutional network
network = input_data(shape=[None, 28, 28, 1], name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 10, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.01,
                     loss='categorical_crossentropy', name='target')


    

In [ ]:

    

# Training
model = tflearn.DNN(network, max_checkpoints=3, 
                   checkpoint_path='/tmp/tflearn_mnist', 
                   best_checkpoint_path='/tmp/tflearn_mnist_best', 
                   tensorboard_verbose=3, 
                   tensorboard_dir='/tmp/tflearn_mnist_logs/')


    

In [ ]:

    

model.load('/tmp/tflearn_mnist-4200')
model.fit({'input': X}, {'target': Y}, n_epoch=1,
           validation_set=({'input': testX}, {'target': testY}),
           snapshot_step=100, show_metric=True, run_id='convnet_mnist')


    

In [ ]: