1. Load dependencies



In [1]:

    
import numpy as np
import tflearn
from tflearn.datasets import mnist

2. Load data



In [2]:

    
MNIST_data = mnist.read_data_sets(one_hot=True)









    



Extracting mnist/train-images-idx3-ubyte.gz






    



/Users/Anirban/anaconda/lib/python2.7/gzip.py:275: VisibleDeprecationWarning: converting an array with ndim > 0 to an index will result in an error in the future
  chunk = self.extrabuf[offset: offset + size]
/Users/Anirban/anaconda/lib/python2.7/site-packages/tflearn/datasets/mnist.py:52: VisibleDeprecationWarning: converting an array with ndim > 0 to an index will result in an error in the future
  data = data.reshape(num_images, rows, cols, 1)






    



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



In [3]:

    
data_train = MNIST_data.train
data_validation = MNIST_data.validation
data_test = MNIST_data.test



In [4]:

    
X, y = data_train._images, data_train._labels

3. Make the model



In [5]:

    
tflearn.init_graph(num_cores=4)

net = tflearn.input_data(shape=[None, 784])
net = tflearn.fully_connected(net, 100, activation='relu')
net = tflearn.fully_connected(net, 100, activation='relu')
net = tflearn.fully_connected(net, 10, activation='softmax')

net = tflearn.regression(net, loss='categorical_crossentropy', optimizer='adam')

model = tflearn.DNN(net)

4. Train the model



In [6]:

    
model.fit(X, y, n_epoch=1, batch_size=10, show_metric=True)









    



Training Step: 5500  | total loss: 0.13695
| Adam | epoch: 001 | loss: 0.13695 - acc: 0.9644 -- iter: 55000/55000
Training Step: 5500  | total loss: 0.13695
| Adam | epoch: 001 | loss: 0.13695 - acc: 0.9644 -- iter: 55000/55000
--