Update examples

examples/trials/mnist-annotation/mnist.py

@@ -157,8 +157,8 @@ def main(params):
     '''
     # Import data
     mnist = input_data.read_data_sets(params['data_dir'], one_hot=True)
-    print('Mnist download data down.')
-    logger.debug('Mnist download data down.')
+    print('Mnist download data done.')
+    logger.debug('Mnist download data done.')
 
     # Create the model
     # Build the graph for the deep net
@@ -180,15 +180,15 @@ def main(params):
     test_acc = 0.0
     with tf.Session() as sess:
         sess.run(tf.global_variables_initializer())
-        """@nni.variable(nni.choice(50, 250, 500), name=batch_num)"""
-        batch_num = params['batch_num']
-        for i in range(batch_num):
-            batch = mnist.train.next_batch(batch_num)
-            """@nni.variable(nni.choice(1, 5), name=dropout_rate)"""
+        """@nni.variable(nni.choice(1, 4, 8, 16, 32), name=batch_size)"""
+        batch_size = params['batch_size']
+        for i in range(params['batch_num']):
+            batch = mnist.train.next_batch(batch_size)
+            """@nni.variable(nni.choice(0.1, 0.2, 0.5, 0.8), name=dropout_rate)"""
             dropout_rate = params['dropout_rate']
             mnist_network.train_step.run(feed_dict={mnist_network.images: batch[0],
                                                     mnist_network.labels: batch[1],
-                                                    mnist_network.keep_prob: dropout_rate}
+                                                    mnist_network.keep_prob: 1 - dropout_rate}
                                         )
 
             if i % 100 == 0:
@@ -224,7 +224,8 @@ def generate_defualt_params():
         'pool_size': 2,
         'hidden_size': 1024,
         'learning_rate': 1e-4,
-        'batch_num': 200}
+        'batch_num': 2000,
+        'batch_size': 32}
     return params
 
 

examples/trials/mnist-smartparam/mnist.py

@@ -180,13 +180,13 @@ def main(params):
     test_acc = 0.0
     with tf.Session() as sess:
         sess.run(tf.global_variables_initializer())
-        batch_num = nni.choice(50, 250, 500, name='batch_num')
-        for i in range(batch_num):
-            batch = mnist.train.next_batch(batch_num)
-            dropout_rate = nni.choice(1, 5, name='dropout_rate')
+        batch_size = nni.choice(1, 4, 8, 16, 32, name='batch_size')
+        for i in range(2000):
+            batch = mnist.train.next_batch(batch_size)
+            dropout_rate = nni.choice(0.1, 0.2, 0.5, 0.8, name='dropout_rate')
             mnist_network.train_step.run(feed_dict={mnist_network.images: batch[0],
                                                     mnist_network.labels: batch[1],
-                                                    mnist_network.keep_prob: dropout_rate}
+                                                    mnist_network.keep_prob: 1 - dropout_rate}
                                         )
 
             if i % 100 == 0:

examples/trials/mnist/config_assessor.yml

@@ -2,7 +2,7 @@ authorName: default
 experimentName: example_mnist
 trialConcurrency: 1
 maxExecDuration: 1h
-maxTrialNum: 1
+maxTrialNum: 100
 #choice: local, remote
 trainingServicePlatform: local
 searchSpacePath: ~/nni/examples/trials/mnist/search_space.json

examples/trials/mnist/mnist.py

@@ -173,10 +173,10 @@ def main(params):
     with tf.Session() as sess:
         sess.run(tf.global_variables_initializer())
         for i in range(params['batch_num']):
-            batch = mnist.train.next_batch(params['batch_num'])
+            batch = mnist.train.next_batch(params['batch_size'])
             mnist_network.train_step.run(feed_dict={mnist_network.images: batch[0],
                                                     mnist_network.labels: batch[1],
-                                                    mnist_network.keep_prob: params['dropout_rate']}
+                                                    mnist_network.keep_prob: 1 - params['dropout_rate']}
                                         )
 
             if i % 100 == 0:
@@ -212,7 +212,8 @@ def generate_default_params():
         'pool_size': 2,
         'hidden_size': 1024,
         'learning_rate': 1e-4,
-        'batch_num': 200}
+        'batch_num': 2000,
+        'batch_size': 32}
     return params
 
 

examples/trials/mnist/search_space.json

@@ -1,6 +1,7 @@
 {
-    "dropout_rate":{"_type":"uniform","_value":[0.1,0.5]},
+    "dropout_rate":{"_type":"uniform","_value":[0.1, 0.2, 0.5, 0.8]},
     "conv_size":{"_type":"choice","_value":[2,3,5,7]},
     "hidden_size":{"_type":"choice","_value":[124, 512, 1024]},
+    "batch_size": {"_type":"choice", "_value": [1, 4, 8, 16, 32]},
     "learning_rate":{"_type":"choice","_value":[0.0001, 0.001, 0.01, 0.1]}
 }