Merge pull request #20 from microsoft/master

pull code

examples/trials/kaggle-tgs-salt/predict.py

@@ -71,7 +71,7 @@ def do_tta_predict(args, model, ckp_path, tta_num=4):
             outputs = np.flip(outputs, 1)
         #print(outputs.shape)
         preds.append(outputs)
-    
+
     parent_dir = ckp_path+'_out'
     if not os.path.exists(parent_dir):
         os.makedirs(parent_dir)
@@ -142,9 +142,9 @@ def generate_preds(outputs, target_size, pad_mode, threshold=0.5):
 
 def ensemble_predict(args):
     model = eval(args.model_name)(args.layers, num_filters=args.nf)
-    
+
     checkpoints = [
-        r'D:\data\salt\models\pseudo\UNetResNetV4_34\edge\best_5.pth', 
+        r'D:\data\salt\models\pseudo\UNetResNetV4_34\edge\best_5.pth',
         r'D:\data\salt\models\pseudo\UNetResNetV4_34\edge\best_6.pth',
         r'D:\data\salt\models\pseudo\UNetResNetV4_34\edge\best_8.pth',
         r'D:\data\salt\models\pseudo\UNetResNetV4_34\edge\best_9.pth'
@@ -160,7 +160,7 @@ def ensemble_np_results(args):
     np_files6 = glob.glob(r'D:\data\salt\models\ensemble\*.npy')
     np_files = np_files1 + np_files2 + np_files3 + np_files6
     print(np_files)
-    ensemble_np(args, np_files) 
+    ensemble_np(args, np_files)
 
 def predict_model(args):
     model = eval(args.model_name)(args.layers, num_filters=args.nf)

examples/trials/kaggle-tgs-salt/preprocess.py

@@ -40,7 +40,7 @@ def prepare_metadata():
                                    )
     meta.to_csv(settings.META_FILE, index=None)
 
-def cov_to_class(val):    
+def cov_to_class(val):
     for i in range(0, 11):
         if val * 10 <= i :
             return i
@@ -57,7 +57,7 @@ def generate_stratified_metadata():
     train_df["file_path_image"] = train_df.index.map(lambda x: os.path.join(settings.TRAIN_IMG_DIR, '{}.png'.format(x)))
     train_df["file_path_mask"] = train_df.index.map(lambda x: os.path.join(settings.TRAIN_MASK_DIR, '{}.png'.format(x)))
 
-    train_df.to_csv(os.path.join(settings.DATA_DIR, 'train_meta2.csv'), 
+    train_df.to_csv(os.path.join(settings.DATA_DIR, 'train_meta2.csv'),
         columns=['file_path_image','file_path_mask','is_train','z','salt_exists', 'coverage_class', 'coverage'])
     train_splits = {}
 
@@ -65,7 +65,7 @@ def generate_stratified_metadata():
     for i, (train_index, valid_index) in enumerate(kf.split(train_df.index.values.reshape(-1), train_df.coverage_class.values.reshape(-1))):
         train_splits[str(i)] = {
             'train_index': train_index.tolist(),
-            'val_index': valid_index.tolist()  
+            'val_index': valid_index.tolist()
         }
     with open(os.path.join(settings.DATA_DIR, 'train_split.json'), 'w') as f:
         json.dump(train_splits, f, indent=4)

examples/trials/kaggle-tgs-salt/train.py

@@ -57,7 +57,7 @@ def weighted_loss(args, output, target, epoch=0):
 
 def train(args):
     print('start training...')
-    
+
     """@nni.variable(nni.choice('UNetResNetV4', 'UNetResNetV5', 'UNetResNetV6'), name=model_name)"""
     model_name = args.model_name
 
@@ -123,10 +123,10 @@ def train(args):
             img, target, salt_target = img.cuda(), target.cuda(), salt_target.cuda()
             optimizer.zero_grad()
             output, salt_out = model(img)
-            
+
             loss, *_ = weighted_loss(args, (output, salt_out), (target, salt_target), epoch=epoch)
             loss.backward()
- 
+
             if args.optim == 'Adam' and args.adamw:
                 wd = 0.0001
                 for group in optimizer.param_groups:
@@ -141,7 +141,7 @@ def train(args):
 
         iout, iou, focal_loss, lovaz_loss, salt_loss, mix_score = validate(args, model, val_loader, epoch=epoch)
         """@nni.report_intermediate_result(iout)"""
-        
+
         _save_ckp = ''
         if iout > best_iout:
             best_iout = iout
@@ -155,7 +155,7 @@ def train(args):
             focal_loss, lovaz_loss, iou, iout, best_iout, (time.time() - bg) / 60, _save_ckp, salt_loss))
 
         model.train()
-        
+
         if args.lrs == 'plateau':
             lr_scheduler.step(best_iout)
         else:
@@ -163,7 +163,7 @@ def train(args):
 
     del model, train_loader, val_loader, optimizer, lr_scheduler
     """@nni.report_final_result(best_iout)"""
-        
+
 def get_lrs(optimizer):
     lrs = []
     for pgs in optimizer.state_dict()['param_groups']:
@@ -188,7 +188,7 @@ def validate(args, model, val_loader, epoch=0, threshold=0.5):
             salt_loss += _salt_loss
             w_loss += _w_loss
             output = torch.sigmoid(output)
-            
+
             for o in output.cpu():
                 outputs.append(o.squeeze().numpy())
 
@@ -217,7 +217,7 @@ def generate_preds(args, outputs, target_size, threshold=0.5):
     return preds
 
 if __name__ == '__main__':
-    
+
     parser = argparse.ArgumentParser(description='TGS Salt segmentation')
     parser.add_argument('--layers', default=34, type=int, help='model layers')
     parser.add_argument('--nf', default=32, type=int, help='num_filters param for model')
@@ -244,7 +244,7 @@ if __name__ == '__main__':
     parser.add_argument('--depths', action='store_true')
     parser.add_argument('--dev_mode', action='store_true')
     parser.add_argument('--adamw', action='store_true')
-    
+
     args = parser.parse_args()
 
     '''@nni.get_next_parameter()'''

examples/trials/kaggle-tgs-salt/utils.py

@@ -166,7 +166,7 @@ def get_nfold_split2(ifold, nfold=10):
     train_index = train_splits[str(ifold)]['train_index']
     valid_index = train_splits[str(ifold)]['val_index']
 
-    return meta_train.iloc[train_index], meta_train.iloc[valid_index] 
+    return meta_train.iloc[train_index], meta_train.iloc[valid_index]
 
 
 def get_test_meta():

examples/trials/mnist-batch-tune-keras/mnist-keras.py

@@ -93,7 +93,7 @@ def train(args, params):
     x_train, y_train, x_test, y_test = load_mnist_data(args)
     model = create_mnist_model(params)
 
-    # nni 
+    # nni
     model.fit(x_train, y_train, batch_size=args.batch_size, epochs=args.epochs, verbose=1,
         validation_data=(x_test, y_test), callbacks=[SendMetrics(), TensorBoard(log_dir=TENSORBOARD_DIR)])
 

examples/trials/mnist-batch-tune-keras/search_space.json

@@ -5,8 +5,8 @@
         "_value" : [{"optimizer": "Adam", "learning_rate": 0.00001},
                     {"optimizer": "Adam", "learning_rate": 0.0001},
                     {"optimizer": "Adam", "learning_rate": 0.001},
-                    {"optimizer": "SGD", "learning_rate": 0.01}, 
-                    {"optimizer": "SGD", "learning_rate": 0.005}, 
+                    {"optimizer": "SGD", "learning_rate": 0.01},
+                    {"optimizer": "SGD", "learning_rate": 0.005},
                     {"optimizer": "SGD", "learning_rate": 0.0002}]
     }
 }
\ No newline at end of file

examples/trials/mnist-distributed-pytorch/dist_mnist.py

@@ -12,10 +12,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# 
-# NNI (https://github.com/Microsoft/nni) modified this code to show how to 
+#
+# NNI (https://github.com/Microsoft/nni) modified this code to show how to
 # integrate distributed pytorch training with NNI SDK
-# 
+#
 
 import os
 import torch

examples/trials/mnist-nas/config.yml

+authorName: default
+experimentName: example_mnist
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: local
+#choice: true, false
+useAnnotation: true
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner
+  #SMAC (SMAC should be installed through nnictl)
+  #codeDir: ~/nni/nni/examples/tuners/random_nas_tuner
+  codeDir: ../../tuners/random_nas_tuner
+  classFileName: random_nas_tuner.py
+  className: RandomNASTuner
+trial:
+  command: python3 mnist.py
+  codeDir: .
+  gpuNum: 0

examples/trials/mnist-nas/mnist.py

+"""A deep MNIST classifier using convolutional layers."""
+
+import argparse
+import logging
+import math
+import tempfile
+import time
+
+import tensorflow as tf
+from tensorflow.examples.tutorials.mnist import input_data
+
+import operators as op
+
+FLAGS = None
+
+logger = logging.getLogger('mnist_AutoML')
+
+
+class MnistNetwork(object):
+    '''
+    MnistNetwork is for initializing and building basic network for mnist.
+    '''
+    def __init__(self,
+                 channel_1_num,
+                 channel_2_num,
+                 conv_size,
+                 hidden_size,
+                 pool_size,
+                 learning_rate,
+                 x_dim=784,
+                 y_dim=10):
+        self.channel_1_num = channel_1_num
+        self.channel_2_num = channel_2_num
+        self.conv_size = conv_size
+        self.hidden_size = hidden_size
+        self.pool_size = pool_size
+        self.learning_rate = learning_rate
+        self.x_dim = x_dim
+        self.y_dim = y_dim
+
+        self.images = tf.placeholder(tf.float32, [None, self.x_dim], name='input_x')
+        self.labels = tf.placeholder(tf.float32, [None, self.y_dim], name='input_y')
+        self.keep_prob = tf.placeholder(tf.float32, name='keep_prob')
+
+        self.train_step = None
+        self.accuracy = None
+
+    def build_network(self):
+        '''
+        Building network for mnist, meanwhile specifying its neural architecture search space
+        '''
+
+        # Reshape to use within a convolutional neural net.
+        # Last dimension is for "features" - there is only one here, since images are
+        # grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
+        with tf.name_scope('reshape'):
+            try:
+                input_dim = int(math.sqrt(self.x_dim))
+            except:
+                print(
+                    'input dim cannot be sqrt and reshape. input dim: ' + str(self.x_dim))
+                logger.debug(
+                    'input dim cannot be sqrt and reshape. input dim: %s', str(self.x_dim))
+                raise
+            x_image = tf.reshape(self.images, [-1, input_dim, input_dim, 1])
+
+        """@nni.mutable_layers(
+            {
+                layer_choice: [op.conv2d(size=1, in_ch=1, out_ch=self.channel_1_num),
+                               op.conv2d(size=3, in_ch=1, out_ch=self.channel_1_num),
+                               op.twice_conv2d(size=3, in_ch=1, out_ch=self.channel_1_num),
+                               op.twice_conv2d(size=7, in_ch=1, out_ch=self.channel_1_num),
+                               op.dilated_conv(in_ch=1, out_ch=self.channel_1_num),
+                               op.separable_conv(size=3, in_ch=1, out_ch=self.channel_1_num),
+                               op.separable_conv(size=5, in_ch=1, out_ch=self.channel_1_num),
+                               op.separable_conv(size=7, in_ch=1, out_ch=self.channel_1_num)],
+                fixed_inputs: [x_image],
+                layer_output: conv1_out
+            },
+            {
+                layer_choice: [op.post_process(ch_size=self.channel_1_num)],
+                fixed_inputs: [conv1_out],
+                layer_output: post1_out
+            },
+            {
+                layer_choice: [op.max_pool(size=3),
+                               op.max_pool(size=5),
+                               op.max_pool(size=7),
+                               op.avg_pool(size=3),
+                               op.avg_pool(size=5),
+                               op.avg_pool(size=7)],
+                fixed_inputs: [post1_out],
+                layer_output: pool1_out
+            },
+            {
+                layer_choice: [op.conv2d(size=1, in_ch=self.channel_1_num, out_ch=self.channel_2_num),
+                               op.conv2d(size=3, in_ch=self.channel_1_num, out_ch=self.channel_2_num),
+                               op.twice_conv2d(size=3, in_ch=self.channel_1_num, out_ch=self.channel_2_num),
+                               op.twice_conv2d(size=7, in_ch=self.channel_1_num, out_ch=self.channel_2_num),
+                               op.dilated_conv(in_ch=self.channel_1_num, out_ch=self.channel_2_num),
+                               op.separable_conv(size=3, in_ch=self.channel_1_num, out_ch=self.channel_2_num),
+                               op.separable_conv(size=5, in_ch=self.channel_1_num, out_ch=self.channel_2_num),
+                               op.separable_conv(size=7, in_ch=self.channel_1_num, out_ch=self.channel_2_num)],
+                fixed_inputs: [pool1_out],
+                optional_inputs: [post1_out],
+                optional_input_size: [0, 1],
+                layer_output: conv2_out
+            },
+            {
+                layer_choice: [op.post_process(ch_size=self.channel_2_num)],
+                fixed_inputs: [conv2_out],
+                layer_output: post2_out
+            },
+            {
+                layer_choice: [op.max_pool(size=3),
+                               op.max_pool(size=5),
+                               op.max_pool(size=7),
+                               op.avg_pool(size=3),
+                               op.avg_pool(size=5),
+                               op.avg_pool(size=7)],
+                fixed_inputs: [post2_out],
+                optional_inputs: [post1_out, pool1_out],
+                optional_input_size: [0, 1],
+                layer_output: pool2_out
+            }
+        )"""
+
+        # Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
+        # is down to 7x7x64 feature maps -- maps this to 1024 features.
+        last_dim_list = pool2_out.get_shape().as_list()
+        assert(last_dim_list[1] == last_dim_list[2])
+        last_dim = last_dim_list[1]
+        with tf.name_scope('fc1'):
+            w_fc1 = op.weight_variable(
+                [last_dim * last_dim * self.channel_2_num, self.hidden_size])
+            b_fc1 = op.bias_variable([self.hidden_size])
+
+        h_pool2_flat = tf.reshape(
+            pool2_out, [-1, last_dim * last_dim * self.channel_2_num])
+        h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)
+
+        # Dropout - controls the complexity of the model, prevents co-adaptation of features.
+        with tf.name_scope('dropout'):
+            h_fc1_drop = tf.nn.dropout(h_fc1, self.keep_prob)
+
+        # Map the 1024 features to 10 classes, one for each digit
+        with tf.name_scope('fc2'):
+            w_fc2 = op.weight_variable([self.hidden_size, self.y_dim])
+            b_fc2 = op.bias_variable([self.y_dim])
+            y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2
+
+        with tf.name_scope('loss'):
+            cross_entropy = tf.reduce_mean(
+                tf.nn.softmax_cross_entropy_with_logits(labels=self.labels, logits=y_conv))
+        with tf.name_scope('adam_optimizer'):
+            self.train_step = tf.train.AdamOptimizer(
+                self.learning_rate).minimize(cross_entropy)
+
+        with tf.name_scope('accuracy'):
+            correct_prediction = tf.equal(
+                tf.argmax(y_conv, 1), tf.argmax(self.labels, 1))
+            self.accuracy = tf.reduce_mean(
+                tf.cast(correct_prediction, tf.float32))
+
+
+def download_mnist_retry(data_dir, max_num_retries=20):
+    """Try to download mnist dataset and avoid errors"""
+    for _ in range(max_num_retries):
+        try:
+            return input_data.read_data_sets(data_dir, one_hot=True)
+        except tf.errors.AlreadyExistsError:
+            time.sleep(1)
+    raise Exception("Failed to download MNIST.")
+
+def main(params):
+    '''
+    Main function, build mnist network, run and send result to NNI.
+    '''
+    # Import data
+    mnist = download_mnist_retry(params['data_dir'])
+    print('Mnist download data done.')
+    logger.debug('Mnist download data done.')
+
+    # Create the model
+    # Build the graph for the deep net
+    mnist_network = MnistNetwork(channel_1_num=params['channel_1_num'],
+                                 channel_2_num=params['channel_2_num'],
+                                 conv_size=params['conv_size'],
+                                 hidden_size=params['hidden_size'],
+                                 pool_size=params['pool_size'],
+                                 learning_rate=params['learning_rate'])
+    mnist_network.build_network()
+    logger.debug('Mnist build network done.')
+
+    # Write log
+    graph_location = tempfile.mkdtemp()
+    logger.debug('Saving graph to: %s', graph_location)
+    train_writer = tf.summary.FileWriter(graph_location)
+    train_writer.add_graph(tf.get_default_graph())
+
+    test_acc = 0.0
+    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_size'])
+            mnist_network.train_step.run(feed_dict={mnist_network.images: batch[0],
+                                                    mnist_network.labels: batch[1],
+                                                    mnist_network.keep_prob: 1 - params['dropout_rate']}
+                                        )
+
+            if i % 100 == 0:
+                test_acc = mnist_network.accuracy.eval(
+                    feed_dict={mnist_network.images: mnist.test.images,
+                               mnist_network.labels: mnist.test.labels,
+                               mnist_network.keep_prob: 1.0})
+
+                """@nni.report_intermediate_result(test_acc)"""
+                logger.debug('test accuracy %g', test_acc)
+                logger.debug('Pipe send intermediate result done.')
+
+        test_acc = mnist_network.accuracy.eval(
+            feed_dict={mnist_network.images: mnist.test.images,
+                       mnist_network.labels: mnist.test.labels,
+                       mnist_network.keep_prob: 1.0})
+
+        """@nni.report_final_result(test_acc)"""
+        logger.debug('Final result is %g', test_acc)
+        logger.debug('Send final result done.')
+
+def get_params():
+    ''' Get parameters from command line '''
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data_dir", type=str, default='/tmp/tensorflow/mnist/input_data', help="data directory")
+    parser.add_argument("--dropout_rate", type=float, default=0.5, help="dropout rate")
+    parser.add_argument("--channel_1_num", type=int, default=32)
+    parser.add_argument("--channel_2_num", type=int, default=64)
+    parser.add_argument("--conv_size", type=int, default=5)
+    parser.add_argument("--pool_size", type=int, default=2)
+    parser.add_argument("--hidden_size", type=int, default=1024)
+    parser.add_argument("--learning_rate", type=float, default=1e-4)
+    parser.add_argument("--batch_num", type=int, default=2000)
+    parser.add_argument("--batch_size", type=int, default=32)
+
+    args, _ = parser.parse_known_args()
+    return args
+
+if __name__ == '__main__':
+    try:
+        params = vars(get_params())
+        main(params)
+    except Exception as exception:
+        logger.exception(exception)
+        raise

examples/trials/mnist-nas/operators.py

+import tensorflow as tf
+import math
+
+
+def weight_variable(shape):
+    """weight_variable generates a weight variable of a given shape."""
+    initial = tf.truncated_normal(shape, stddev=0.1)
+    return tf.Variable(initial)
+
+def bias_variable(shape):
+    """bias_variable generates a bias variable of a given shape."""
+    initial = tf.constant(0.1, shape=shape)
+    return tf.Variable(initial)
+
+def sum_op(inputs):
+    """sum_op"""
+    fixed_input = inputs[0][0]
+    optional_input = inputs[1][0]
+    fixed_shape = fixed_input.get_shape().as_list()
+    optional_shape = optional_input.get_shape().as_list()
+    assert fixed_shape[1] == fixed_shape[2]
+    assert optional_shape[1] == optional_shape[2]
+    pool_size = math.ceil(optional_shape[1] / fixed_shape[1])
+    pool_out = tf.nn.avg_pool(optional_input, ksize=[1, pool_size, pool_size, 1], strides=[1, pool_size, pool_size, 1], padding='SAME')
+    conv_matrix = weight_variable([1, 1, optional_shape[3], fixed_shape[3]])
+    conv_out = tf.nn.conv2d(pool_out, conv_matrix, strides=[1, 1, 1, 1], padding='SAME')
+    return fixed_input + conv_out
+
+
+def conv2d(inputs, size=-1, in_ch=-1, out_ch=-1):
+    """conv2d returns a 2d convolution layer with full stride."""
+    if not inputs[1]:
+        x_input = inputs[0][0]
+    else:
+        x_input = sum_op(inputs)
+    if size in [1, 3]:
+        w_matrix = weight_variable([size, size, in_ch, out_ch])
+        return tf.nn.conv2d(x_input, w_matrix, strides=[1, 1, 1, 1], padding='SAME')
+    else:
+        raise Exception("Unknown filter size: %d." % size)
+
+def twice_conv2d(inputs, size=-1, in_ch=-1, out_ch=-1):
+    """twice_conv2d"""
+    if not inputs[1]:
+        x_input = inputs[0][0]
+    else:
+        x_input = sum_op(inputs)
+    if size in  [3, 7]:
+        w_matrix1 = weight_variable([1, size, in_ch, int(out_ch/2)])
+        out = tf.nn.conv2d(x_input, w_matrix1, strides=[1, 1, 1, 1], padding='SAME')
+        w_matrix2 = weight_variable([size, 1, int(out_ch/2), out_ch])
+        return tf.nn.conv2d(out, w_matrix2, strides=[1, 1, 1, 1], padding='SAME')
+    else:
+        raise Exception("Unknown filter size: %d." % size)
+
+def dilated_conv(inputs, size=3, in_ch=-1, out_ch=-1):
+    """dilated_conv"""
+    if not inputs[1]:
+        x_input = inputs[0][0]
+    else:
+        x_input = sum_op(inputs)
+    if size == 3:
+        w_matrix = weight_variable([size, size, in_ch, out_ch])
+        return tf.nn.atrous_conv2d(x_input, w_matrix, rate=2, padding='SAME')
+    else:
+        raise Exception("Unknown filter size: %d." % size)
+
+def separable_conv(inputs, size=-1, in_ch=-1, out_ch=-1):
+    """separable_conv"""
+    if not inputs[1]:
+        x_input = inputs[0][0]
+    else:
+        x_input = sum_op(inputs)
+    if size in [3, 5, 7]:
+        depth_matrix = weight_variable([size, size, in_ch, 1])
+        point_matrix = weight_variable([1, 1, 1*in_ch, out_ch])
+        return tf.nn.separable_conv2d(x_input, depth_matrix, point_matrix, strides=[1, 1, 1, 1], padding='SAME')
+    else:
+        raise Exception("Unknown filter size: %d." % size)
+
+
+def avg_pool(inputs, size=-1):
+    """avg_pool downsamples a feature map."""
+    if not inputs[1]:
+        x_input = inputs[0][0]
+    else:
+        x_input = sum_op(inputs)
+    if size in [3, 5, 7]:
+        return tf.nn.avg_pool(x_input, ksize=[1, size, size, 1], strides=[1, size, size, 1], padding='SAME')
+    else:
+        raise Exception("Unknown filter size: %d." % size)
+
+def max_pool(inputs, size=-1):
+    """max_pool downsamples a feature map."""
+    if not inputs[1]:
+        x_input = inputs[0][0]
+    else:
+        x_input = sum_op(inputs)
+    if size in [3, 5, 7]:
+        return tf.nn.max_pool(x_input, ksize=[1, size, size, 1], strides=[1, size, size, 1], padding='SAME')
+    else:
+        raise Exception("Unknown filter size: %d." % size)
+
+
+def post_process(inputs, ch_size=-1):
+    """post_process"""
+    x_input = inputs[0][0]
+    bias_matrix = bias_variable([ch_size])
+    return tf.nn.relu(x_input + bias_matrix)

examples/trials/mnist-nested-search-space/mnist.py

@@ -121,7 +121,7 @@ def main(params):
         for i in range(params['batch_num']):
             batch = mnist.train.next_batch(params['batch_size'])
             mnist_network.train_step.run(feed_dict={mnist_network.x: batch[0], mnist_network.y: batch[1]})
-            
+
             if i % 100 == 0:
                 train_accuracy = mnist_network.accuracy.eval(feed_dict={
                     mnist_network.x: batch[0], mnist_network.y: batch[1]})

examples/trials/NAS/README.md → examples/trials/nas_cifar10/README.md

- **Run Neural Network Architecture Search in NNI**	
- ===	
- 
-Now we have an NAS example [NNI-NAS-Example](https://github.com/Crysple/NNI-NAS-Example) run in NNI using NAS interface from our contributors.	
- 
-Thanks our lovely contributors. 	
- 
-And welcome more and more people to join us!
+ **Run Neural Network Architecture Search in NNI**	
+ ===	
+ 
+Now we have an NAS example [NNI-NAS-Example](https://github.com/Crysple/NNI-NAS-Example) run in NNI using NAS interface from our contributors.	
+ 
+Thanks our lovely contributors. 	
+ 
+And welcome more and more people to join us!
\ No newline at end of file

examples/trials/nas_cifar10/README_zh_CN.md

+**在 NNI 中运行神经网络架构搜索**  
+===
+
+参考 [NNI-NAS-Example](https://github.com/Crysple/NNI-NAS-Example)，来使用贡献者提供的 NAS 接口。
+
+谢谢可爱的贡献者！
+
+欢迎越来越多的人加入我们！
\ No newline at end of file

examples/trials/network_morphism/FashionMNIST/config.yml

@@ -10,7 +10,7 @@ trainingServicePlatform: local
 useAnnotation: false
 tuner:
   #choice: TPE, Random, Anneal, Evolution, BatchTuner, NetworkMorphism
-  #SMAC (SMAC should be installed through nnictl) 
+  #SMAC (SMAC should be installed through nnictl)
   builtinTunerName: NetworkMorphism
   classArgs:
     #choice: maximize, minimize

examples/trials/network_morphism/FashionMNIST/config_pai.yml

@@ -9,7 +9,7 @@ trainingServicePlatform: pai
 useAnnotation: false
 tuner:
   #choice: TPE, Random, Anneal, Evolution, BatchTuner, NetworkMorphism
-  #SMAC (SMAC should be installed through nnictl) 
+  #SMAC (SMAC should be installed through nnictl)
   builtinTunerName: NetworkMorphism
   classArgs:
     #choice: maximize, minimize

examples/trials/network_morphism/README.md

@@ -8,7 +8,7 @@ The Network Morphism is a build-in Tuner using network morphism techniques to se
 The network morphism now is framework-based, and we have not implemented the framework-free methods. The training frameworks which we have supported yet are PyTorch and Keras. If you get familiar with the intermediate JSON format, you can build your own model in your own training framework. In the future, we will change to intermediate format from JSON to ONNX in order to get a [standard intermediate representation spec](https://github.com/onnx/onnx/blob/master/docs/IR.md).
 
 
-### 2. Install the requirements 
+### 2. Install the requirements
 
 ```bash
 # install the requirements packages
@@ -32,7 +32,7 @@ trainingServicePlatform: local
 useAnnotation: false
 tuner:
   #choice: TPE, Random, Anneal, Evolution, BatchTuner, NetworkMorphism
-  #SMAC (SMAC should be installed through nnictl) 
+  #SMAC (SMAC should be installed through nnictl)
   builtinTunerName: NetworkMorphism
   classArgs:
     #choice: maximize, minimize
@@ -83,7 +83,7 @@ net = build_graph_from_json(RCV_CONFIG)
 nni.report_final_result(best_acc)
 ```
 
-### 5. Submit this job 
+### 5. Submit this job
 
 ```bash
 # You can use NNI command tool "nnictl" to create the a job which submit to the NNI

examples/trials/network_morphism/README_zh_CN.md

@@ -99,10 +99,10 @@ nnictl create --config config.yml
 
 `Fashion-MNIST` 是来自 [Zalando](https://jobs.zalando.com/tech/) 文章的图片 — 有 60,000 个样例的训练集和 10,000 个样例的测试集。 每个样例是 28x28 的灰度图，分为 10 个类别。 由于 MNIST 数据集过于简单，该数据集现在开始被广泛使用，用来替换 MNIST 作为基准数据集。
 
-这里有两个样例，[FashionMNIST-keras.py](../../../../examples/trials/network_morphism/FashionMNIST/FashionMNIST_keras.py) 和 [FashionMNIST-pytorch.py](../../../../examples/trials/network_morphism/FashionMNIST/FashionMNIST_pytorch.py)。 注意，在 `config.yml` 中，需要为此数据集修改 `input_width` 为 28，以及 `input_channel` 为 1。
+这里有两个样例，[FashionMNIST-keras.py](./FashionMNIST/FashionMNIST_keras.py) 和 [FashionMNIST-pytorch.py](./FashionMNIST/FashionMNIST_pytorch.py)。 注意，在 `config.yml` 中，需要为此数据集修改 `input_width` 为 28，以及 `input_channel` 为 1。
 
 ### Cifar10
 
 `CIFAR-10` 数据集 [Canadian Institute For Advanced Research](https://www.cifar.ca/) 是广泛用于机器学习和视觉算法训练的数据集。 它是机器学习领域最广泛使用的数据集之一。 CIFAR-10 数据集包含了 60,000 张 32x32 的彩色图片，分为 10 类。
 
-这里有两个样例，[cifar10-keras.py](../../../../examples/trials/network_morphism/cifar10/cifar10_keras.py) 和 [cifar10-pytorch.py](../../../../examples/trials/network_morphism/cifar10/cifar10_pytorch.py)。 在 `config.yml` 中，该数据集 `input_width` 的值是 32，并且 `input_channel` 是 3。
+这里有两个样例，[cifar10-keras.py](./cifar10/cifar10_keras.py) 和 [cifar10-pytorch.py](./cifar10/cifar10_pytorch.py)。 在 `config.yml` 中，该数据集 `input_width` 的值是 32，并且 `input_channel` 是 3。
\ No newline at end of file

examples/trials/network_morphism/cifar10/config.yml

@@ -10,7 +10,7 @@ trainingServicePlatform: local
 useAnnotation: false
 tuner:
   #choice: TPE, Random, Anneal, Evolution, BatchTuner, NetworkMorphism
-  #SMAC (SMAC should be installed through nnictl) 
+  #SMAC (SMAC should be installed through nnictl)
   builtinTunerName: NetworkMorphism
   classArgs:
     #choice: maximize, minimize

examples/trials/network_morphism/cifar10/config_pai.yml

@@ -9,7 +9,7 @@ trainingServicePlatform: pai
 useAnnotation: false
 tuner:
   #choice: TPE, Random, Anneal, Evolution, BatchTuner, NetworkMorphism
-  #SMAC (SMAC should be installed through nnictl) 
+  #SMAC (SMAC should be installed through nnictl)
   builtinTunerName: NetworkMorphism
   classArgs:
     #choice: maximize, minimize

examples/trials/sklearn/classification/main.py

@@ -56,7 +56,7 @@ def get_model(PARAMS):
     model.degree = PARAMS.get('degree')
     model.gamma = PARAMS.get('gamma')
     model.coef0 = PARAMS.get('coef0')
-    
+
     return model
 
 def run(X_train, X_test, y_train, y_test, PARAMS):