• API
• FAQ
• Tools
• Archive
SHARE
TWEET

# Untitled

a guest Mar 18th, 2019 63 Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
1. import tensorflow as tf
2. from tensorflow.examples.tutorials.mnist import input_data
3. mnist = input_data.read_data_sets("/tmp/data/", one_hot = True)
4.
5. batch_size = 100
6.
7. #MODEL
8.
9. def neural_network_model(data):
10.     weights = {'W_conv': tf.Variable(tf.random_normal([5,5,1,32])),
11.                'W_fc': tf.Variable(tf.random_normal([14*14*32,100])),
12.                'W_out': tf.Variable(tf.random_normal([100,10])),}
13.
14.
15.     biases = {'b_conv':tf.Variable(tf.random_normal([32])),
16.               'b_fc':tf.Variable(tf.random_normal([100])),
17.               'b_out':tf.Variable(tf.random_normal([10])),
18.              }
19.
20.     x = tf.reshape(data,shape=[-1,28,28,1])
21.
22.     c = tf.nn.conv2d(x,weights['W_conv'], strides = [1,1,1,1],padding= 'SAME')
23.     c += biases["b_conv"]
24.     c = tf.nn.relu(c)
25.
26.     m = tf.nn.max_pool(c,ksize=[1,2,2,1], strides = [1,2,2,1], padding = "SAME")
27.
28.
29.     fc = tf.reshape(m,[-1,14*14*32])
31.
32.     output = tf.nn.relu(tf.matmul(fc,weights['W_out'])+biases["b_out"])
33.
34.
35.     return output
36.
37.
38. #GRAF
39.
40. x = tf.placeholder('float',[None,784])
41. y = tf.placeholder('float')
42.
43. predictions = neural_network_model(x)
44. cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=predictions,labels=y))
45.
47.
48. saver = tf.train.Saver()
49.
50. # WYWOŁANIE SESJI
51.
52. hm_epochs =3
53.
54. with tf.Session() as sess:
55.
56.     sess.run(tf.global_variables_initializer())
57.
58.     for epoch in range(hm_epochs):
59.
60.         epoch_loss =0
61.         for _ in range(int(mnist.train.num_examples/batch_size)):
62.             epoch_x,epoch_y = mnist.train.next_batch(batch_size)
63.             _, c = sess.run([optimizer,cost],feed_dict = {x:epoch_x,y:epoch_y})
64.             epoch_loss +=c
65.         print("Epoch",epoch,'completed out of',hm_epochs,'loss:', epoch_loss)
66.
67.
68.
69.     correct = tf.equal(tf.argmax(predictions,1), tf.argmax(y,1))
70.     accuracy = tf.reduce_mean(tf.cast(correct,'float'))
71.     print("Accuracy:",accuracy.eval({x:mnist.train.images, y:mnist.train.labels}))
72.
73.
74.     save_path = saver.save(sess, "/tmp/model.ckpt")
RAW Paste Data
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.

Top