added alexnet & update loss

alexnet.py

@@ -0,0 +1,99 @@
+# Import MINST data
+import input_data
+mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
+
+import tensorflow as tf
+
+# Parameters
+learning_rate = 0.001
+training_iters = 200000
+batch_size = 64
+display_step = 20
+
+#Network Parameters
+n_input = 784 #MNIST data input
+n_classes = 10 #MNIST total classes
+dropout = 0.8
+
+# Create model
+x = tf.placeholder(tf.types.float32, [None, n_input])
+y = tf.placeholder(tf.types.float32, [None, n_classes])
+keep_prob = tf.placeholder(tf.types.float32) #dropout
+
+def conv2d(name, l_input, w, b):
+    return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)
+
+def max_pool(name, l_input, k):
+    return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)
+
+def norm(name, l_input, lsize=4):
+    return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)
+
+def conv_net(_X, _weights, _biases, _dropout):
+    _X = tf.reshape(_X, shape=[-1, 28, 28, 1])
+
+    conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
+    pool1 = max_pool('pool1', conv1, k=2)
+    norm1 = norm('norm1', pool1, lsize=4)
+    norm1 = tf.nn.dropout(norm1, _dropout)
+
+    conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
+    pool2 = max_pool('pool2', conv2, k=2)
+    norm2 = norm('norm2', pool2, lsize=4)
+    norm2 = tf.nn.dropout(norm2, _dropout)
+
+    conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
+    pool3 = max_pool('pool3', conv3, k=2)
+    norm3 = norm('norm3', pool3, lsize=4)
+    norm3 = tf.nn.dropout(norm3, _dropout)
+
+    dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]])
+    dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')
+
+    dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2')
+
+    out = tf.matmul(dense2, _weights['out']) + _biases['out']
+    return out
+
+weights = {
+    'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),
+    'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
+    'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
+    'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])),
+    'wd2': tf.Variable(tf.random_normal([1024, 1024])),
+    'out': tf.Variable(tf.random_normal([1024, 10]))
+}
+
+biases = {
+    'bc1': tf.Variable(tf.random_normal([64])),
+    'bc2': tf.Variable(tf.random_normal([128])),
+    'bc3': tf.Variable(tf.random_normal([256])),
+    'bd1': tf.Variable(tf.random_normal([1024])),
+    'bd2': tf.Variable(tf.random_normal([1024])),
+    'out': tf.Variable(tf.random_normal([n_classes]))
+}
+
+pred = conv_net(x, weights, biases, keep_prob)
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
+optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
+
+#Evaluate model
+correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
+accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.types.float32))
+
+# Train
+init = tf.initialize_all_variables()
+with tf.Session() as sess:
+    sess.run(init)
+    step = 1
+    while step * batch_size < training_iters:
+        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
+        sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
+        if step % display_step == 0:
+            acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
+            loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
+            print "Iter " + str(step*batch_size) + ", Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
+        step += 1
+    print "Optimization Finished!"
+    #Accuracy on 256 mnist test images
+    print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})

convolutional_network.py

@@ -21,7 +21,7 @@ y = tf.placeholder(tf.types.float32, [None, n_classes])
 keep_prob = tf.placeholder(tf.types.float32) #dropout
 
 def conv2d(img, w, b):
-    return tf.nn.relu(tf.nn.conv2d(img, w, strides=[1, 1, 1, 1], padding='SAME') + b)
+    return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(img, w, strides=[1, 1, 1, 1], padding='SAME'),b))
 
 def max_pool(img, k):
     return tf.nn.max_pool(img, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')
@@ -67,18 +67,16 @@ correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
 accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.types.float32))
 
 # Train
-#load mnist data
 init = tf.initialize_all_variables()
 with tf.Session() as sess:
     sess.run(init)
     step = 1
-    avg_cost = 0.
     while step * batch_size < training_iters:
         batch_xs, batch_ys = mnist.train.next_batch(batch_size)
         sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
         if step % display_step == 0:
-            avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})/batch_size
-            print "Iter", str(step*batch_size), "cost=", "{:.9f}".format(avg_cost/step)
+            loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})/batch_size
+            print "Iter", str(step*batch_size), "loss=", "{:.9f}".format(loss/step)
         step += 1
     print "Optimization Finished!"
     #Accuracy on 256 mnist test images