Create a gist now

Instantly share code, notes, and snippets.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
from PIL import Image, ImageOps
import numpy as np
FLAGS = None
def predict(x, W1, b1, W2, b2):
a1 = tf.matmul(x, W1) + b1
z1 = tf.sigmoid(a1)
a2 = tf.matmul(z1, W2) + b2
y = tf.nn.softmax(a2)
return y
def get_result(sess, image_filenames, W1, b1, W2, b2):
data = []
for filename in image_filenames:
img = np.array("L"))
data.append(tf.constant((255 - img.flatten())/255, dtype=tf.float32))
result =, W1, b1, W2, b2))
result = np.argmax(result, axis=1)
return result
def main(_):
# Import data
mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
# Create the model
std = 0.01
x = tf.placeholder(tf.float32, [None, 784])
W1 = tf.Variable(tf.random_normal([784, 100], stddev=std))
b1 = tf.Variable(tf.zeros([100]))
W2 = tf.Variable(tf.random_normal([100, 10], stddev=std))
b2 = tf.Variable(tf.zeros([10]))
y = predict(x, W1, b1, W2, b2)
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.InteractiveSession()
# Train
for _ in range(10000):
batch_xs, batch_ys = mnist.train.next_batch(100), feed_dict={x: batch_xs, y_: batch_ys})
# Test
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(, feed_dict={x: mnist.test.images,
y_: mnist.test.labels}))
print(get_result(sess, ['1.png', '5.png', '7.png'], W1, b1, W2, b2))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
help='Directory for storing input data')
FLAGS, unparsed = parser.parse_known_args(), argv=[sys.argv[0]] + unparsed)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment