Merge pull request #366 from nathansilberman/master

Full code refactor and added all networks

slim/nets/alexnet.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Contains a model definition for AlexNet.
+
+This work was first described in:
+  ImageNet Classification with Deep Convolutional Neural Networks
+  Alex Krizhevsky, Ilya Sutskever and Geoffrey E. Hinton
+
+and later refined in:
+  One weird trick for parallelizing convolutional neural networks
+  Alex Krizhevsky, 2014
+
+Here we provide the implementation proposed in "One weird trick" and not
+"ImageNet Classification", as per the paper, the LRN layers have been removed.
+
+Usage:
+  with slim.arg_scope(alexnet.alexnet_v2_arg_scope()):
+    outputs, end_points = alexnet.alexnet_v2(inputs)
+
+@@alexnet_v2
+"""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import tensorflow as tf
+
+slim = tf.contrib.slim
+trunc_normal = lambda stddev: tf.truncated_normal_initializer(0.0, stddev)
+
+
+def alexnet_v2_arg_scope(weight_decay=0.0005):
+  with slim.arg_scope([slim.conv2d, slim.fully_connected],
+                      activation_fn=tf.nn.relu,
+                      biases_initializer=tf.constant_initializer(0.1),
+                      weights_regularizer=slim.l2_regularizer(weight_decay)):
+    with slim.arg_scope([slim.conv2d], padding='SAME'):
+      with slim.arg_scope([slim.max_pool2d], padding='VALID') as arg_sc:
+        return arg_sc
+
+
+def alexnet_v2(inputs,
+               num_classes=1000,
+               is_training=True,
+               dropout_keep_prob=0.5,
+               spatial_squeeze=True,
+               scope='alexnet_v2'):
+  """AlexNet version 2.
+
+  Described in: http://arxiv.org/pdf/1404.5997v2.pdf
+  Parameters from:
+  github.com/akrizhevsky/cuda-convnet2/blob/master/layers/
+  layers-imagenet-1gpu.cfg
+
+  Note: All the fully_connected layers have been transformed to conv2d layers.
+        To use in classification mode, resize input to 224x224. To use in fully
+        convolutional mode, set spatial_squeeze to false.
+        The LRN layers have been removed and change the initializers from
+        random_normal_initializer to xavier_initializer.
+
+  Args:
+    inputs: a tensor of size [batch_size, height, width, channels].
+    num_classes: number of predicted classes.
+    is_training: whether or not the model is being trained.
+    dropout_keep_prob: the probability that activations are kept in the dropout
+      layers during training.
+    spatial_squeeze: whether or not should squeeze the spatial dimensions of the
+      outputs. Useful to remove unnecessary dimensions for classification.
+    scope: Optional scope for the variables.
+
+  Returns:
+    the last op containing the log predictions and end_points dict.
+  """
+  with tf.variable_scope(scope, 'alexnet_v2', [inputs]) as sc:
+    end_points_collection = sc.name + '_end_points'
+    # Collect outputs for conv2d, fully_connected and max_pool2d.
+    with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d],
+                        outputs_collections=[end_points_collection]):
+      net = slim.conv2d(inputs, 64, [11, 11], 4, padding='VALID',
+                        scope='conv1')
+      net = slim.max_pool2d(net, [3, 3], 2, scope='pool1')
+      net = slim.conv2d(net, 192, [5, 5], scope='conv2')
+      net = slim.max_pool2d(net, [3, 3], 2, scope='pool2')
+      net = slim.conv2d(net, 384, [3, 3], scope='conv3')
+      net = slim.conv2d(net, 384, [3, 3], scope='conv4')
+      net = slim.conv2d(net, 256, [3, 3], scope='conv5')
+      net = slim.max_pool2d(net, [3, 3], 2, scope='pool5')
+
+      # Use conv2d instead of fully_connected layers.
+      with slim.arg_scope([slim.conv2d],
+                          weights_initializer=trunc_normal(0.005),
+                          biases_initializer=tf.constant_initializer(0.1)):
+        net = slim.conv2d(net, 4096, [5, 5], padding='VALID',
+                          scope='fc6')
+        net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
+                           scope='dropout6')
+        net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
+        net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
+                           scope='dropout7')
+        net = slim.conv2d(net, num_classes, [1, 1],
+                          activation_fn=None,
+                          normalizer_fn=None,
+                          biases_initializer=tf.zeros_initializer,
+                          scope='fc8')
+
+      # Convert end_points_collection into a end_point dict.
+      end_points = dict(tf.get_collection(end_points_collection))
+      if spatial_squeeze:
+        net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
+        end_points[sc.name + '/fc8'] = net
+      return net, end_points
+alexnet_v2.default_image_size = 224

slim/nets/alexnet_test.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Tests for slim.nets.alexnet."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import tensorflow as tf
+
+from nets import alexnet
+
+slim = tf.contrib.slim
+
+
+class AlexnetV2Test(tf.test.TestCase):
+
+  def testBuild(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      logits, _ = alexnet.alexnet_v2(inputs, num_classes)
+      self.assertEquals(logits.op.name, 'alexnet_v2/fc8/squeezed')
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+
+  def testFullyConvolutional(self):
+    batch_size = 1
+    height, width = 300, 400
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      logits, _ = alexnet.alexnet_v2(inputs, num_classes, spatial_squeeze=False)
+      self.assertEquals(logits.op.name, 'alexnet_v2/fc8/BiasAdd')
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, 4, 7, num_classes])
+
+  def testEndPoints(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      _, end_points = alexnet.alexnet_v2(inputs, num_classes)
+      expected_names = ['alexnet_v2/conv1',
+                        'alexnet_v2/pool1',
+                        'alexnet_v2/conv2',
+                        'alexnet_v2/pool2',
+                        'alexnet_v2/conv3',
+                        'alexnet_v2/conv4',
+                        'alexnet_v2/conv5',
+                        'alexnet_v2/pool5',
+                        'alexnet_v2/fc6',
+                        'alexnet_v2/fc7',
+                        'alexnet_v2/fc8'
+                       ]
+      self.assertSetEqual(set(end_points.keys()), set(expected_names))
+
+  def testModelVariables(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      alexnet.alexnet_v2(inputs, num_classes)
+      expected_names = ['alexnet_v2/conv1/weights',
+                        'alexnet_v2/conv1/biases',
+                        'alexnet_v2/conv2/weights',
+                        'alexnet_v2/conv2/biases',
+                        'alexnet_v2/conv3/weights',
+                        'alexnet_v2/conv3/biases',
+                        'alexnet_v2/conv4/weights',
+                        'alexnet_v2/conv4/biases',
+                        'alexnet_v2/conv5/weights',
+                        'alexnet_v2/conv5/biases',
+                        'alexnet_v2/fc6/weights',
+                        'alexnet_v2/fc6/biases',
+                        'alexnet_v2/fc7/weights',
+                        'alexnet_v2/fc7/biases',
+                        'alexnet_v2/fc8/weights',
+                        'alexnet_v2/fc8/biases',
+                       ]
+      model_variables = [v.op.name for v in slim.get_model_variables()]
+      self.assertSetEqual(set(model_variables), set(expected_names))
+
+  def testEvaluation(self):
+    batch_size = 2
+    height, width = 224, 224
+    num_classes = 1000
+    with self.test_session():
+      eval_inputs = tf.random_uniform((batch_size, height, width, 3))
+      logits, _ = alexnet.alexnet_v2(eval_inputs, is_training=False)
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+      predictions = tf.argmax(logits, 1)
+      self.assertListEqual(predictions.get_shape().as_list(), [batch_size])
+
+  def testTrainEvalWithReuse(self):
+    train_batch_size = 2
+    eval_batch_size = 1
+    train_height, train_width = 224, 224
+    eval_height, eval_width = 300, 400
+    num_classes = 1000
+    with self.test_session():
+      train_inputs = tf.random_uniform(
+          (train_batch_size, train_height, train_width, 3))
+      logits, _ = alexnet.alexnet_v2(train_inputs)
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [train_batch_size, num_classes])
+      tf.get_variable_scope().reuse_variables()
+      eval_inputs = tf.random_uniform(
+          (eval_batch_size, eval_height, eval_width, 3))
+      logits, _ = alexnet.alexnet_v2(eval_inputs, is_training=False,
+                                     spatial_squeeze=False)
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [eval_batch_size, 4, 7, num_classes])
+      logits = tf.reduce_mean(logits, [1, 2])
+      predictions = tf.argmax(logits, 1)
+      self.assertEquals(predictions.get_shape().as_list(), [eval_batch_size])
+
+  def testForward(self):
+    batch_size = 1
+    height, width = 224, 224
+    with self.test_session() as sess:
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      logits, _ = alexnet.alexnet_v2(inputs)
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(logits)
+      self.assertTrue(output.any())
+
+if __name__ == '__main__':
+  tf.test.main()

slim/nets/cifarnet.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Contains a variant of the CIFAR-10 model definition."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import tensorflow as tf
+
+slim = tf.contrib.slim
+
+trunc_normal = lambda stddev: tf.truncated_normal_initializer(stddev=stddev)
+
+
+def cifarnet(images, num_classes=10, is_training=False,
+             dropout_keep_prob=0.5,
+             prediction_fn=slim.softmax,
+             scope='CifarNet'):
+  """Creates a variant of the CifarNet model.
+
+  Note that since the output is a set of 'logits', the values fall in the
+  interval of (-infinity, infinity). Consequently, to convert the outputs to a
+  probability distribution over the characters, one will need to convert them
+  using the softmax function:
+
+        logits = cifarnet.cifarnet(images, is_training=False)
+        probabilities = tf.nn.softmax(logits)
+        predictions = tf.argmax(logits, 1)
+
+  Args:
+    images: A batch of `Tensors` of size [batch_size, height, width, channels].
+    num_classes: the number of classes in the dataset.
+    is_training: specifies whether or not we're currently training the model.
+      This variable will determine the behaviour of the dropout layer.
+    dropout_keep_prob: the percentage of activation values that are retained.
+    prediction_fn: a function to get predictions out of logits.
+    scope: Optional variable_scope.
+
+  Returns:
+    logits: the pre-softmax activations, a tensor of size
+      [batch_size, `num_classes`]
+    end_points: a dictionary from components of the network to the corresponding
+      activation.
+  """
+  end_points = {}
+
+  with tf.variable_scope(scope, 'CifarNet', [images, num_classes]):
+    net = slim.conv2d(images, 64, [5, 5], scope='conv1')
+    end_points['conv1'] = net
+    net = slim.max_pool2d(net, [2, 2], 2, scope='pool1')
+    end_points['pool1'] = net
+    net = tf.nn.lrn(net, 4, bias=1.0, alpha=0.001/9.0, beta=0.75, name='norm1')
+    net = slim.conv2d(net, 64, [5, 5], scope='conv2')
+    end_points['conv2'] = net
+    net = tf.nn.lrn(net, 4, bias=1.0, alpha=0.001/9.0, beta=0.75, name='norm2')
+    net = slim.max_pool2d(net, [2, 2], 2, scope='pool2')
+    end_points['pool2'] = net
+    net = slim.flatten(net)
+    end_points['Flatten'] = net
+    net = slim.fully_connected(net, 384, scope='fc3')
+    end_points['fc3'] = net
+    net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
+                       scope='dropout3')
+    net = slim.fully_connected(net, 192, scope='fc4')
+    end_points['fc4'] = net
+    logits = slim.fully_connected(net, num_classes,
+                                  biases_initializer=tf.zeros_initializer,
+                                  weights_initializer=trunc_normal(1/192.0),
+                                  weights_regularizer=None,
+                                  activation_fn=None,
+                                  scope='logits')
+
+    end_points['Logits'] = logits
+    end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
+
+  return logits, end_points
+cifarnet.default_image_size = 32
+
+
+def cifarnet_arg_scope(weight_decay=0.004):
+  """Defines the default cifarnet argument scope.
+
+  Args:
+    weight_decay: The weight decay to use for regularizing the model.
+
+  Returns:
+    An `arg_scope` to use for the inception v3 model.
+  """
+  with slim.arg_scope(
+      [slim.conv2d],
+      weights_initializer=tf.truncated_normal_initializer(stddev=5e-2),
+      activation_fn=tf.nn.relu):
+    with slim.arg_scope(
+        [slim.fully_connected],
+        biases_initializer=tf.constant_initializer(0.1),
+        weights_initializer=trunc_normal(0.04),
+        weights_regularizer=slim.l2_regularizer(weight_decay),
+        activation_fn=tf.nn.relu) as sc:
+      return sc

slim/nets/inception.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Brings inception_v1, inception_v2 and inception_v3 under one namespace."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+# pylint: disable=unused-import
+from nets.inception_resnet_v2 import inception_resnet_v2
+from nets.inception_resnet_v2 import inception_resnet_v2_arg_scope
+from nets.inception_v1 import inception_v1
+from nets.inception_v1 import inception_v1_arg_scope
+from nets.inception_v1 import inception_v1_base
+from nets.inception_v2 import inception_v2
+from nets.inception_v2 import inception_v2_arg_scope
+from nets.inception_v2 import inception_v2_base
+from nets.inception_v3 import inception_v3
+from nets.inception_v3 import inception_v3_arg_scope
+from nets.inception_v3 import inception_v3_base
+# pylint: enable=unused-import

slim/nets/inception_resnet_v2.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Contains the definition of the Inception Resnet V2 architecture.
+
+As described in http://arxiv.org/abs/1602.07261.
+
+  Inception-v4, Inception-ResNet and the Impact of Residual Connections
+    on Learning
+  Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alex Alemi
+"""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+import tensorflow as tf
+
+slim = tf.contrib.slim
+
+
+def block35(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
+  """Builds the 35x35 resnet block."""
+  with tf.variable_scope(scope, 'Block35', [net], reuse=reuse):
+    with tf.variable_scope('Branch_0'):
+      tower_conv = slim.conv2d(net, 32, 1, scope='Conv2d_1x1')
+    with tf.variable_scope('Branch_1'):
+      tower_conv1_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
+      tower_conv1_1 = slim.conv2d(tower_conv1_0, 32, 3, scope='Conv2d_0b_3x3')
+    with tf.variable_scope('Branch_2'):
+      tower_conv2_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
+      tower_conv2_1 = slim.conv2d(tower_conv2_0, 48, 3, scope='Conv2d_0b_3x3')
+      tower_conv2_2 = slim.conv2d(tower_conv2_1, 64, 3, scope='Conv2d_0c_3x3')
+    mixed = tf.concat(3, [tower_conv, tower_conv1_1, tower_conv2_2])
+    up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
+                     activation_fn=None, scope='Conv2d_1x1')
+    net += scale * up
+    if activation_fn:
+      net = activation_fn(net)
+  return net
+
+
+def block17(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
+  """Builds the 17x17 resnet block."""
+  with tf.variable_scope(scope, 'Block17', [net], reuse=reuse):
+    with tf.variable_scope('Branch_0'):
+      tower_conv = slim.conv2d(net, 192, 1, scope='Conv2d_1x1')
+    with tf.variable_scope('Branch_1'):
+      tower_conv1_0 = slim.conv2d(net, 128, 1, scope='Conv2d_0a_1x1')
+      tower_conv1_1 = slim.conv2d(tower_conv1_0, 160, [1, 7],
+                                  scope='Conv2d_0b_1x7')
+      tower_conv1_2 = slim.conv2d(tower_conv1_1, 192, [7, 1],
+                                  scope='Conv2d_0c_7x1')
+    mixed = tf.concat(3, [tower_conv, tower_conv1_2])
+    up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
+                     activation_fn=None, scope='Conv2d_1x1')
+    net += scale * up
+    if activation_fn:
+      net = activation_fn(net)
+  return net
+
+
+def block8(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
+  """Builds the 8x8 resnet block."""
+  with tf.variable_scope(scope, 'Block8', [net], reuse=reuse):
+    with tf.variable_scope('Branch_0'):
+      tower_conv = slim.conv2d(net, 192, 1, scope='Conv2d_1x1')
+    with tf.variable_scope('Branch_1'):
+      tower_conv1_0 = slim.conv2d(net, 192, 1, scope='Conv2d_0a_1x1')
+      tower_conv1_1 = slim.conv2d(tower_conv1_0, 224, [1, 3],
+                                  scope='Conv2d_0b_1x3')
+      tower_conv1_2 = slim.conv2d(tower_conv1_1, 256, [3, 1],
+                                  scope='Conv2d_0c_3x1')
+    mixed = tf.concat(3, [tower_conv, tower_conv1_2])
+    up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
+                     activation_fn=None, scope='Conv2d_1x1')
+    net += scale * up
+    if activation_fn:
+      net = activation_fn(net)
+  return net
+
+
+def inception_resnet_v2(inputs, num_classes=1001, is_training=True,
+                        dropout_keep_prob=0.8,
+                        reuse=None,
+                        scope='InceptionResnetV2'):
+  """Creates the Inception Resnet V2 model.
+
+  Args:
+    inputs: a 4-D tensor of size [batch_size, height, width, 3].
+    num_classes: number of predicted classes.
+    is_training: whether is training or not.
+    dropout_keep_prob: float, the fraction to keep before final layer.
+    reuse: whether or not the network and its variables should be reused. To be
+      able to reuse 'scope' must be given.
+    scope: Optional variable_scope.
+
+  Returns:
+    logits: the logits outputs of the model.
+    end_points: the set of end_points from the inception model.
+  """
+  end_points = {}
+
+  with tf.variable_scope(scope, 'InceptionResnetV2', [inputs], reuse=reuse):
+    with slim.arg_scope([slim.batch_norm, slim.dropout],
+                        is_training=is_training):
+      with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
+                          stride=1, padding='SAME'):
+
+        # 149 x 149 x 32
+        net = slim.conv2d(inputs, 32, 3, stride=2, padding='VALID',
+                          scope='Conv2d_1a_3x3')
+        end_points['Conv2d_1a_3x3'] = net
+        # 147 x 147 x 32
+        net = slim.conv2d(net, 32, 3, padding='VALID',
+                          scope='Conv2d_2a_3x3')
+        end_points['Conv2d_2a_3x3'] = net
+        # 147 x 147 x 64
+        net = slim.conv2d(net, 64, 3, scope='Conv2d_2b_3x3')
+        end_points['Conv2d_2b_3x3'] = net
+        # 73 x 73 x 64
+        net = slim.max_pool2d(net, 3, stride=2, padding='VALID',
+                              scope='MaxPool_3a_3x3')
+        end_points['MaxPool_3a_3x3'] = net
+        # 73 x 73 x 80
+        net = slim.conv2d(net, 80, 1, padding='VALID',
+                          scope='Conv2d_3b_1x1')
+        end_points['Conv2d_3b_1x1'] = net
+        # 71 x 71 x 192
+        net = slim.conv2d(net, 192, 3, padding='VALID',
+                          scope='Conv2d_4a_3x3')
+        end_points['Conv2d_4a_3x3'] = net
+        # 35 x 35 x 192
+        net = slim.max_pool2d(net, 3, stride=2, padding='VALID',
+                              scope='MaxPool_5a_3x3')
+        end_points['MaxPool_5a_3x3'] = net
+
+        # 35 x 35 x 320
+        with tf.variable_scope('Mixed_5b'):
+          with tf.variable_scope('Branch_0'):
+            tower_conv = slim.conv2d(net, 96, 1, scope='Conv2d_1x1')
+          with tf.variable_scope('Branch_1'):
+            tower_conv1_0 = slim.conv2d(net, 48, 1, scope='Conv2d_0a_1x1')
+            tower_conv1_1 = slim.conv2d(tower_conv1_0, 64, 5,
+                                        scope='Conv2d_0b_5x5')
+          with tf.variable_scope('Branch_2'):
+            tower_conv2_0 = slim.conv2d(net, 64, 1, scope='Conv2d_0a_1x1')
+            tower_conv2_1 = slim.conv2d(tower_conv2_0, 96, 3,
+                                        scope='Conv2d_0b_3x3')
+            tower_conv2_2 = slim.conv2d(tower_conv2_1, 96, 3,
+                                        scope='Conv2d_0c_3x3')
+          with tf.variable_scope('Branch_3'):
+            tower_pool = slim.avg_pool2d(net, 3, stride=1, padding='SAME',
+                                         scope='AvgPool_0a_3x3')
+            tower_pool_1 = slim.conv2d(tower_pool, 64, 1,
+                                       scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [tower_conv, tower_conv1_1,
+                              tower_conv2_2, tower_pool_1])
+
+        end_points['Mixed_5b'] = net
+        net = slim.repeat(net, 10, block35, scale=0.17)
+
+        # 17 x 17 x 1024
+        with tf.variable_scope('Mixed_6a'):
+          with tf.variable_scope('Branch_0'):
+            tower_conv = slim.conv2d(net, 384, 3, stride=2, padding='VALID',
+                                     scope='Conv2d_1a_3x3')
+          with tf.variable_scope('Branch_1'):
+            tower_conv1_0 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
+            tower_conv1_1 = slim.conv2d(tower_conv1_0, 256, 3,
+                                        scope='Conv2d_0b_3x3')
+            tower_conv1_2 = slim.conv2d(tower_conv1_1, 384, 3,
+                                        stride=2, padding='VALID',
+                                        scope='Conv2d_1a_3x3')
+          with tf.variable_scope('Branch_2'):
+            tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID',
+                                         scope='MaxPool_1a_3x3')
+          net = tf.concat(3, [tower_conv, tower_conv1_2, tower_pool])
+
+        end_points['Mixed_6a'] = net
+        net = slim.repeat(net, 20, block17, scale=0.10)
+
+        # Auxillary tower
+        with tf.variable_scope('AuxLogits'):
+          aux = slim.avg_pool2d(net, 5, stride=3, padding='VALID',
+                                scope='Conv2d_1a_3x3')
+          aux = slim.conv2d(aux, 128, 1, scope='Conv2d_1b_1x1')
+          aux = slim.conv2d(aux, 768, aux.get_shape()[1:3],
+                            padding='VALID', scope='Conv2d_2a_5x5')
+          aux = slim.flatten(aux)
+          aux = slim.fully_connected(aux, num_classes, activation_fn=None,
+                                     scope='Logits')
+          end_points['AuxLogits'] = aux
+
+        with tf.variable_scope('Mixed_7a'):
+          with tf.variable_scope('Branch_0'):
+            tower_conv = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
+            tower_conv_1 = slim.conv2d(tower_conv, 384, 3, stride=2,
+                                       padding='VALID', scope='Conv2d_1a_3x3')
+          with tf.variable_scope('Branch_1'):
+            tower_conv1 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
+            tower_conv1_1 = slim.conv2d(tower_conv1, 288, 3, stride=2,
+                                        padding='VALID', scope='Conv2d_1a_3x3')
+          with tf.variable_scope('Branch_2'):
+            tower_conv2 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
+            tower_conv2_1 = slim.conv2d(tower_conv2, 288, 3,
+                                        scope='Conv2d_0b_3x3')
+            tower_conv2_2 = slim.conv2d(tower_conv2_1, 320, 3, stride=2,
+                                        padding='VALID', scope='Conv2d_1a_3x3')
+          with tf.variable_scope('Branch_3'):
+            tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID',
+                                         scope='MaxPool_1a_3x3')
+          net = tf.concat(3, [tower_conv_1, tower_conv1_1,
+                              tower_conv2_2, tower_pool])
+
+        end_points['Mixed_7a'] = net
+
+        net = slim.repeat(net, 9, block8, scale=0.20)
+        net = block8(net, activation_fn=None)
+
+        net = slim.conv2d(net, 1536, 1, scope='Conv2d_7b_1x1')
+        end_points['Conv2d_7b_1x1'] = net
+
+        with tf.variable_scope('Logits'):
+          end_points['PrePool'] = net
+          net = slim.avg_pool2d(net, net.get_shape()[1:3], padding='VALID',
+                                scope='AvgPool_1a_8x8')
+          net = slim.flatten(net)
+
+          net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
+                             scope='Dropout')
+
+          end_points['PreLogitsFlatten'] = net
+          logits = slim.fully_connected(net, num_classes, activation_fn=None,
+                                        scope='Logits')
+          end_points['Logits'] = logits
+          end_points['Predictions'] = tf.nn.softmax(logits, name='Predictions')
+
+    return logits, end_points
+inception_resnet_v2.default_image_size = 299
+
+
+def inception_resnet_v2_arg_scope(weight_decay=0.00004,
+                                  batch_norm_decay=0.9997,
+                                  batch_norm_epsilon=0.001):
+  """Yields the scope with the default parameters for inception_resnet_v2.
+
+  Args:
+    weight_decay: the weight decay for weights variables.
+    batch_norm_decay: decay for the moving average of batch_norm momentums.
+    batch_norm_epsilon: small float added to variance to avoid dividing by zero.
+
+  Returns:
+    a arg_scope with the parameters needed for inception_resnet_v2.
+  """
+  # Set weight_decay for weights in conv2d and fully_connected layers.
+  with slim.arg_scope([slim.conv2d, slim.fully_connected],
+                      weights_regularizer=slim.l2_regularizer(weight_decay),
+                      biases_regularizer=slim.l2_regularizer(weight_decay)):
+
+    batch_norm_params = {
+        'decay': batch_norm_decay,
+        'epsilon': batch_norm_epsilon,
+    }
+    # Set activation_fn and parameters for batch_norm.
+    with slim.arg_scope([slim.conv2d], activation_fn=tf.nn.relu,
+                        normalizer_fn=slim.batch_norm,
+                        normalizer_params=batch_norm_params) as scope:
+      return scope

slim/nets/inception_resnet_v2_test.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Tests for slim.inception_resnet_v2."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import tensorflow as tf
+
+from nets import inception
+
+
+class InceptionTest(tf.test.TestCase):
+
+  def testBuildLogits(self):
+    batch_size = 5
+    height, width = 299, 299
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      logits, _ = inception.inception_resnet_v2(inputs, num_classes)
+      self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+
+  def testBuildEndPoints(self):
+    batch_size = 5
+    height, width = 299, 299
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      _, end_points = inception.inception_resnet_v2(inputs, num_classes)
+      self.assertTrue('Logits' in end_points)
+      logits = end_points['Logits']
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+      self.assertTrue('AuxLogits' in end_points)
+      aux_logits = end_points['AuxLogits']
+      self.assertListEqual(aux_logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+      pre_pool = end_points['PrePool']
+      self.assertListEqual(pre_pool.get_shape().as_list(),
+                           [batch_size, 8, 8, 1536])
+
+  def testVariablesSetDevice(self):
+    batch_size = 5
+    height, width = 299, 299
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      # Force all Variables to reside on the device.
+      with tf.variable_scope('on_cpu'), tf.device('/cpu:0'):
+        inception.inception_resnet_v2(inputs, num_classes)
+      with tf.variable_scope('on_gpu'), tf.device('/gpu:0'):
+        inception.inception_resnet_v2(inputs, num_classes)
+      for v in tf.get_collection(tf.GraphKeys.VARIABLES, scope='on_cpu'):
+        self.assertDeviceEqual(v.device, '/cpu:0')
+      for v in tf.get_collection(tf.GraphKeys.VARIABLES, scope='on_gpu'):
+        self.assertDeviceEqual(v.device, '/gpu:0')
+
+  def testHalfSizeImages(self):
+    batch_size = 5
+    height, width = 150, 150
+    num_classes = 1000
+    with self.test_session():
+      inputs = tf.random_uniform((batch_size, height, width, 3))
+      logits, end_points = inception.inception_resnet_v2(inputs, num_classes)
+      self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+      pre_pool = end_points['PrePool']
+      self.assertListEqual(pre_pool.get_shape().as_list(),
+                           [batch_size, 3, 3, 1536])
+
+  def testUnknownBatchSize(self):
+    batch_size = 1
+    height, width = 299, 299
+    num_classes = 1000
+    with self.test_session() as sess:
+      inputs = tf.placeholder(tf.float32, (None, height, width, 3))
+      logits, _ = inception.inception_resnet_v2(inputs, num_classes)
+      self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [None, num_classes])
+      images = tf.random_uniform((batch_size, height, width, 3))
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(logits, {inputs: images.eval()})
+      self.assertEquals(output.shape, (batch_size, num_classes))
+
+  def testEvaluation(self):
+    batch_size = 2
+    height, width = 299, 299
+    num_classes = 1000
+    with self.test_session() as sess:
+      eval_inputs = tf.random_uniform((batch_size, height, width, 3))
+      logits, _ = inception.inception_resnet_v2(eval_inputs,
+                                                num_classes,
+                                                is_training=False)
+      predictions = tf.argmax(logits, 1)
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(predictions)
+      self.assertEquals(output.shape, (batch_size,))
+
+  def testTrainEvalWithReuse(self):
+    train_batch_size = 5
+    eval_batch_size = 2
+    height, width = 150, 150
+    num_classes = 1000
+    with self.test_session() as sess:
+      train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
+      inception.inception_resnet_v2(train_inputs, num_classes)
+      eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
+      logits, _ = inception.inception_resnet_v2(eval_inputs,
+                                                num_classes,
+                                                is_training=False,
+                                                reuse=True)
+      predictions = tf.argmax(logits, 1)
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(predictions)
+      self.assertEquals(output.shape, (eval_batch_size,))
+
+
+if __name__ == '__main__':
+  tf.test.main()

slim/nets/inception_v1.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Contains the definition for inception v1 classification network."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import tensorflow as tf
+
+slim = tf.contrib.slim
+trunc_normal = lambda stddev: tf.truncated_normal_initializer(0.0, stddev)
+
+
+def inception_v1_base(inputs,
+                      final_endpoint='Mixed_5c',
+                      scope='InceptionV1'):
+  """Defines the Inception V1 base architecture.
+
+  This architecture is defined in:
+    Going deeper with convolutions
+    Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed,
+    Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich.
+    http://arxiv.org/pdf/1409.4842v1.pdf.
+
+  Args:
+    inputs: a tensor of size [batch_size, height, width, channels].
+    final_endpoint: specifies the endpoint to construct the network up to. It
+      can be one of ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
+      'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
+      'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e',
+      'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b', 'Mixed_5c']
+    scope: Optional variable_scope.
+
+  Returns:
+    A dictionary from components of the network to the corresponding activation.
+
+  Raises:
+    ValueError: if final_endpoint is not set to one of the predefined values.
+  """
+  end_points = {}
+  with tf.variable_scope(scope, 'InceptionV1', [inputs]):
+    with slim.arg_scope(
+        [slim.conv2d, slim.fully_connected],
+        weights_initializer=trunc_normal(0.01)):
+      with slim.arg_scope([slim.conv2d, slim.max_pool2d],
+                          stride=1, padding='SAME'):
+        end_point = 'Conv2d_1a_7x7'
+        net = slim.conv2d(inputs, 64, [7, 7], stride=2, scope=end_point)
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+        end_point = 'MaxPool_2a_3x3'
+        net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+        end_point = 'Conv2d_2b_1x1'
+        net = slim.conv2d(net, 64, [1, 1], scope=end_point)
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+        end_point = 'Conv2d_2c_3x3'
+        net = slim.conv2d(net, 192, [3, 3], scope=end_point)
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+        end_point = 'MaxPool_3a_3x3'
+        net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_3b'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 96, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 128, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 16, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 32, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 32, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_3c'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 192, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'MaxPool_4a_3x3'
+        net = slim.max_pool2d(net, [3, 3], stride=2, scope=end_point)
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_4b'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 96, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 208, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 16, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 48, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_4c'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 112, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 224, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 24, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_4d'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 256, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 24, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_4e'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 112, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 144, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 288, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 64, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_4f'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 256, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 320, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'MaxPool_5a_2x2'
+        net = slim.max_pool2d(net, [2, 2], stride=2, scope=end_point)
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_5b'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 256, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 320, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 32, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0a_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+
+        end_point = 'Mixed_5c'
+        with tf.variable_scope(end_point):
+          with tf.variable_scope('Branch_0'):
+            branch_0 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1')
+          with tf.variable_scope('Branch_1'):
+            branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
+            branch_1 = slim.conv2d(branch_1, 384, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_2'):
+            branch_2 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0a_1x1')
+            branch_2 = slim.conv2d(branch_2, 128, [3, 3], scope='Conv2d_0b_3x3')
+          with tf.variable_scope('Branch_3'):
+            branch_3 = slim.max_pool2d(net, [3, 3], scope='MaxPool_0a_3x3')
+            branch_3 = slim.conv2d(branch_3, 128, [1, 1], scope='Conv2d_0b_1x1')
+          net = tf.concat(3, [branch_0, branch_1, branch_2, branch_3])
+        end_points[end_point] = net
+        if final_endpoint == end_point: return net, end_points
+    raise ValueError('Unknown final endpoint %s' % final_endpoint)
+
+
+def inception_v1(inputs,
+                 num_classes=1000,
+                 is_training=True,
+                 dropout_keep_prob=0.8,
+                 prediction_fn=slim.softmax,
+                 spatial_squeeze=True,
+                 reuse=None,
+                 scope='InceptionV1'):
+  """Defines the Inception V1 architecture.
+
+  This architecture is defined in:
+
+    Going deeper with convolutions
+    Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed,
+    Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich.
+    http://arxiv.org/pdf/1409.4842v1.pdf.
+
+  The default image size used to train this network is 224x224.
+
+  Args:
+    inputs: a tensor of size [batch_size, height, width, channels].
+    num_classes: number of predicted classes.
+    is_training: whether is training or not.
+    dropout_keep_prob: the percentage of activation values that are retained.
+    prediction_fn: a function to get predictions out of logits.
+    spatial_squeeze: if True, logits is of shape is [B, C], if false logits is
+        of shape [B, 1, 1, C], where B is batch_size and C is number of classes.
+    reuse: whether or not the network and its variables should be reused. To be
+      able to reuse 'scope' must be given.
+    scope: Optional variable_scope.
+
+  Returns:
+    logits: the pre-softmax activations, a tensor of size
+      [batch_size, num_classes]
+    end_points: a dictionary from components of the network to the corresponding
+      activation.
+  """
+  # Final pooling and prediction
+  with tf.variable_scope(scope, 'InceptionV1', [inputs, num_classes],
+                         reuse=reuse) as scope:
+    with slim.arg_scope([slim.batch_norm, slim.dropout],
+                        is_training=is_training):
+      net, end_points = inception_v1_base(inputs, scope=scope)
+      with tf.variable_scope('Logits'):
+        net = slim.avg_pool2d(net, [7, 7], stride=1, scope='MaxPool_0a_7x7')
+        net = slim.dropout(net,
+                           dropout_keep_prob, scope='Dropout_0b')
+        logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
+                             normalizer_fn=None, scope='Conv2d_0c_1x1')
+        if spatial_squeeze:
+          logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
+
+        end_points['Logits'] = logits
+        end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
+  return logits, end_points
+inception_v1.default_image_size = 224
+
+
+def inception_v1_arg_scope(weight_decay=0.00004,
+                           use_batch_norm=True):
+  """Defines the default InceptionV1 arg scope.
+
+  Note: Althougth the original paper didn't use batch_norm we found it useful.
+
+  Args:
+    weight_decay: The weight decay to use for regularizing the model.
+    use_batch_norm: "If `True`, batch_norm is applied after each convolution.
+
+  Returns:
+    An `arg_scope` to use for the inception v3 model.
+  """
+  batch_norm_params = {
+      # Decay for the moving averages.
+      'decay': 0.9997,
+      # epsilon to prevent 0s in variance.
+      'epsilon': 0.001,
+      # collection containing update_ops.
+      'updates_collections': tf.GraphKeys.UPDATE_OPS,
+  }
+  if use_batch_norm:
+    normalizer_fn = slim.batch_norm
+    normalizer_params = batch_norm_params
+  else:
+    normalizer_fn = None
+    normalizer_params = {}
+  # Set weight_decay for weights in Conv and FC layers.
+  with slim.arg_scope([slim.conv2d, slim.fully_connected],
+                      weights_regularizer=slim.l2_regularizer(weight_decay)):
+    with slim.arg_scope(
+        [slim.conv2d],
+        weights_initializer=slim.variance_scaling_initializer(),
+        activation_fn=tf.nn.relu,
+        normalizer_fn=normalizer_fn,
+        normalizer_params=normalizer_params) as sc:
+      return sc

slim/nets/inception_v1_test.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Tests for nets.inception_v1."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import numpy as np
+import tensorflow as tf
+
+from nets import inception
+
+slim = tf.contrib.slim
+
+
+class InceptionV1Test(tf.test.TestCase):
+
+  def testBuildClassificationNetwork(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    logits, end_points = inception.inception_v1(inputs, num_classes)
+    self.assertTrue(logits.op.name.startswith('InceptionV1/Logits'))
+    self.assertListEqual(logits.get_shape().as_list(),
+                         [batch_size, num_classes])
+    self.assertTrue('Predictions' in end_points)
+    self.assertListEqual(end_points['Predictions'].get_shape().as_list(),
+                         [batch_size, num_classes])
+
+  def testBuildBaseNetwork(self):
+    batch_size = 5
+    height, width = 224, 224
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    mixed_6c, end_points = inception.inception_v1_base(inputs)
+    self.assertTrue(mixed_6c.op.name.startswith('InceptionV1/Mixed_5c'))
+    self.assertListEqual(mixed_6c.get_shape().as_list(),
+                         [batch_size, 7, 7, 1024])
+    expected_endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
+                          'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b',
+                          'Mixed_3c', 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c',
+                          'Mixed_4d', 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2',
+                          'Mixed_5b', 'Mixed_5c']
+    self.assertItemsEqual(end_points.keys(), expected_endpoints)
+
+  def testBuildOnlyUptoFinalEndpoint(self):
+    batch_size = 5
+    height, width = 224, 224
+    endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
+                 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
+                 'MaxPool_4a_3x3', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d',
+                 'Mixed_4e', 'Mixed_4f', 'MaxPool_5a_2x2', 'Mixed_5b',
+                 'Mixed_5c']
+    for index, endpoint in enumerate(endpoints):
+      with tf.Graph().as_default():
+        inputs = tf.random_uniform((batch_size, height, width, 3))
+        out_tensor, end_points = inception.inception_v1_base(
+            inputs, final_endpoint=endpoint)
+        self.assertTrue(out_tensor.op.name.startswith(
+            'InceptionV1/' + endpoint))
+        self.assertItemsEqual(endpoints[:index+1], end_points)
+
+  def testBuildAndCheckAllEndPointsUptoMixed5c(self):
+    batch_size = 5
+    height, width = 224, 224
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    _, end_points = inception.inception_v1_base(inputs,
+                                                final_endpoint='Mixed_5c')
+    endpoints_shapes = {'Conv2d_1a_7x7': [5, 112, 112, 64],
+                        'MaxPool_2a_3x3': [5, 56, 56, 64],
+                        'Conv2d_2b_1x1': [5, 56, 56, 64],
+                        'Conv2d_2c_3x3': [5, 56, 56, 192],
+                        'MaxPool_3a_3x3': [5, 28, 28, 192],
+                        'Mixed_3b': [5, 28, 28, 256],
+                        'Mixed_3c': [5, 28, 28, 480],
+                        'MaxPool_4a_3x3': [5, 14, 14, 480],
+                        'Mixed_4b': [5, 14, 14, 512],
+                        'Mixed_4c': [5, 14, 14, 512],
+                        'Mixed_4d': [5, 14, 14, 512],
+                        'Mixed_4e': [5, 14, 14, 528],
+                        'Mixed_4f': [5, 14, 14, 832],
+                        'MaxPool_5a_2x2': [5, 7, 7, 832],
+                        'Mixed_5b': [5, 7, 7, 832],
+                        'Mixed_5c': [5, 7, 7, 1024]}
+
+    self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
+    for endpoint_name in endpoints_shapes:
+      expected_shape = endpoints_shapes[endpoint_name]
+      self.assertTrue(endpoint_name in end_points)
+      self.assertListEqual(end_points[endpoint_name].get_shape().as_list(),
+                           expected_shape)
+
+  def testModelHasExpectedNumberOfParameters(self):
+    batch_size = 5
+    height, width = 224, 224
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    with slim.arg_scope(inception.inception_v1_arg_scope()):
+      inception.inception_v1_base(inputs)
+    total_params, _ = slim.model_analyzer.analyze_vars(
+        slim.get_model_variables())
+    self.assertAlmostEqual(5607184, total_params)
+
+  def testHalfSizeImages(self):
+    batch_size = 5
+    height, width = 112, 112
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    mixed_5c, _ = inception.inception_v1_base(inputs)
+    self.assertTrue(mixed_5c.op.name.startswith('InceptionV1/Mixed_5c'))
+    self.assertListEqual(mixed_5c.get_shape().as_list(),
+                         [batch_size, 4, 4, 1024])
+
+  def testUnknownImageShape(self):
+    tf.reset_default_graph()
+    batch_size = 2
+    height, width = 224, 224
+    num_classes = 1000
+    input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
+    with self.test_session() as sess:
+      inputs = tf.placeholder(tf.float32, shape=(batch_size, None, None, 3))
+      logits, end_points = inception.inception_v1(inputs, num_classes)
+      self.assertTrue(logits.op.name.startswith('InceptionV1/Logits'))
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+      pre_pool = end_points['Mixed_5c']
+      feed_dict = {inputs: input_np}
+      tf.initialize_all_variables().run()
+      pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
+      self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
+
+  def testUnknowBatchSize(self):
+    batch_size = 1
+    height, width = 224, 224
+    num_classes = 1000
+
+    inputs = tf.placeholder(tf.float32, (None, height, width, 3))
+    logits, _ = inception.inception_v1(inputs, num_classes)
+    self.assertTrue(logits.op.name.startswith('InceptionV1/Logits'))
+    self.assertListEqual(logits.get_shape().as_list(),
+                         [None, num_classes])
+    images = tf.random_uniform((batch_size, height, width, 3))
+
+    with self.test_session() as sess:
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(logits, {inputs: images.eval()})
+      self.assertEquals(output.shape, (batch_size, num_classes))
+
+  def testEvaluation(self):
+    batch_size = 2
+    height, width = 224, 224
+    num_classes = 1000
+
+    eval_inputs = tf.random_uniform((batch_size, height, width, 3))
+    logits, _ = inception.inception_v1(eval_inputs, num_classes,
+                                       is_training=False)
+    predictions = tf.argmax(logits, 1)
+
+    with self.test_session() as sess:
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(predictions)
+      self.assertEquals(output.shape, (batch_size,))
+
+  def testTrainEvalWithReuse(self):
+    train_batch_size = 5
+    eval_batch_size = 2
+    height, width = 224, 224
+    num_classes = 1000
+
+    train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
+    inception.inception_v1(train_inputs, num_classes)
+    eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
+    logits, _ = inception.inception_v1(eval_inputs, num_classes, reuse=True)
+    predictions = tf.argmax(logits, 1)
+
+    with self.test_session() as sess:
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(predictions)
+      self.assertEquals(output.shape, (eval_batch_size,))
+
+  def testLogitsNotSqueezed(self):
+    num_classes = 25
+    images = tf.random_uniform([1, 224, 224, 3])
+    logits, _ = inception.inception_v1(images,
+                                       num_classes=num_classes,
+                                       spatial_squeeze=False)
+
+    with self.test_session() as sess:
+      tf.initialize_all_variables().run()
+      logits_out = sess.run(logits)
+      self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
+
+
+if __name__ == '__main__':
+  tf.test.main()

slim/nets/inception_v2_test.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Tests for nets.inception_v2."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import numpy as np
+import tensorflow as tf
+
+from nets import inception
+
+slim = tf.contrib.slim
+
+
+class InceptionV2Test(tf.test.TestCase):
+
+  def testBuildClassificationNetwork(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    logits, end_points = inception.inception_v2(inputs, num_classes)
+    self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
+    self.assertListEqual(logits.get_shape().as_list(),
+                         [batch_size, num_classes])
+    self.assertTrue('Predictions' in end_points)
+    self.assertListEqual(end_points['Predictions'].get_shape().as_list(),
+                         [batch_size, num_classes])
+
+  def testBuildBaseNetwork(self):
+    batch_size = 5
+    height, width = 224, 224
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    mixed_5c, end_points = inception.inception_v2_base(inputs)
+    self.assertTrue(mixed_5c.op.name.startswith('InceptionV2/Mixed_5c'))
+    self.assertListEqual(mixed_5c.get_shape().as_list(),
+                         [batch_size, 7, 7, 1024])
+    expected_endpoints = ['Mixed_3b', 'Mixed_3c', 'Mixed_4a', 'Mixed_4b',
+                          'Mixed_4c', 'Mixed_4d', 'Mixed_4e', 'Mixed_5a',
+                          'Mixed_5b', 'Mixed_5c', 'Conv2d_1a_7x7',
+                          'MaxPool_2a_3x3', 'Conv2d_2b_1x1', 'Conv2d_2c_3x3',
+                          'MaxPool_3a_3x3']
+    self.assertItemsEqual(end_points.keys(), expected_endpoints)
+
+  def testBuildOnlyUptoFinalEndpoint(self):
+    batch_size = 5
+    height, width = 224, 224
+    endpoints = ['Conv2d_1a_7x7', 'MaxPool_2a_3x3', 'Conv2d_2b_1x1',
+                 'Conv2d_2c_3x3', 'MaxPool_3a_3x3', 'Mixed_3b', 'Mixed_3c',
+                 'Mixed_4a', 'Mixed_4b', 'Mixed_4c', 'Mixed_4d', 'Mixed_4e',
+                 'Mixed_5a', 'Mixed_5b', 'Mixed_5c']
+    for index, endpoint in enumerate(endpoints):
+      with tf.Graph().as_default():
+        inputs = tf.random_uniform((batch_size, height, width, 3))
+        out_tensor, end_points = inception.inception_v2_base(
+            inputs, final_endpoint=endpoint)
+        self.assertTrue(out_tensor.op.name.startswith(
+            'InceptionV2/' + endpoint))
+        self.assertItemsEqual(endpoints[:index+1], end_points)
+
+  def testBuildAndCheckAllEndPointsUptoMixed5c(self):
+    batch_size = 5
+    height, width = 224, 224
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    _, end_points = inception.inception_v2_base(inputs,
+                                                final_endpoint='Mixed_5c')
+    endpoints_shapes = {'Mixed_3b': [batch_size, 28, 28, 256],
+                        'Mixed_3c': [batch_size, 28, 28, 320],
+                        'Mixed_4a': [batch_size, 14, 14, 576],
+                        'Mixed_4b': [batch_size, 14, 14, 576],
+                        'Mixed_4c': [batch_size, 14, 14, 576],
+                        'Mixed_4d': [batch_size, 14, 14, 576],
+                        'Mixed_4e': [batch_size, 14, 14, 576],
+                        'Mixed_5a': [batch_size, 7, 7, 1024],
+                        'Mixed_5b': [batch_size, 7, 7, 1024],
+                        'Mixed_5c': [batch_size, 7, 7, 1024],
+                        'Conv2d_1a_7x7': [batch_size, 112, 112, 64],
+                        'MaxPool_2a_3x3': [batch_size, 56, 56, 64],
+                        'Conv2d_2b_1x1': [batch_size, 56, 56, 64],
+                        'Conv2d_2c_3x3': [batch_size, 56, 56, 192],
+                        'MaxPool_3a_3x3': [batch_size, 28, 28, 192]}
+    self.assertItemsEqual(endpoints_shapes.keys(), end_points.keys())
+    for endpoint_name in endpoints_shapes:
+      expected_shape = endpoints_shapes[endpoint_name]
+      self.assertTrue(endpoint_name in end_points)
+      self.assertListEqual(end_points[endpoint_name].get_shape().as_list(),
+                           expected_shape)
+
+  def testModelHasExpectedNumberOfParameters(self):
+    batch_size = 5
+    height, width = 224, 224
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    with slim.arg_scope(inception.inception_v2_arg_scope()):
+      inception.inception_v2_base(inputs)
+    total_params, _ = slim.model_analyzer.analyze_vars(
+        slim.get_model_variables())
+    self.assertAlmostEqual(10173112, total_params)
+
+  def testBuildEndPointsWithDepthMultiplierLessThanOne(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    _, end_points = inception.inception_v2(inputs, num_classes)
+
+    endpoint_keys = [key for key in end_points.keys()
+                     if key.startswith('Mixed') or key.startswith('Conv')]
+
+    _, end_points_with_multiplier = inception.inception_v2(
+        inputs, num_classes, scope='depth_multiplied_net',
+        depth_multiplier=0.5)
+
+    for key in endpoint_keys:
+      original_depth = end_points[key].get_shape().as_list()[3]
+      new_depth = end_points_with_multiplier[key].get_shape().as_list()[3]
+      self.assertEqual(0.5 * original_depth, new_depth)
+
+  def testBuildEndPointsWithDepthMultiplierGreaterThanOne(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    _, end_points = inception.inception_v2(inputs, num_classes)
+
+    endpoint_keys = [key for key in end_points.keys()
+                     if key.startswith('Mixed') or key.startswith('Conv')]
+
+    _, end_points_with_multiplier = inception.inception_v2(
+        inputs, num_classes, scope='depth_multiplied_net',
+        depth_multiplier=2.0)
+
+    for key in endpoint_keys:
+      original_depth = end_points[key].get_shape().as_list()[3]
+      new_depth = end_points_with_multiplier[key].get_shape().as_list()[3]
+      self.assertEqual(2.0 * original_depth, new_depth)
+
+  def testRaiseValueErrorWithInvalidDepthMultiplier(self):
+    batch_size = 5
+    height, width = 224, 224
+    num_classes = 1000
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    with self.assertRaises(ValueError):
+      _ = inception.inception_v2(inputs, num_classes, depth_multiplier=-0.1)
+    with self.assertRaises(ValueError):
+      _ = inception.inception_v2(inputs, num_classes, depth_multiplier=0.0)
+
+  def testHalfSizeImages(self):
+    batch_size = 5
+    height, width = 112, 112
+    num_classes = 1000
+
+    inputs = tf.random_uniform((batch_size, height, width, 3))
+    logits, end_points = inception.inception_v2(inputs, num_classes)
+    self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
+    self.assertListEqual(logits.get_shape().as_list(),
+                         [batch_size, num_classes])
+    pre_pool = end_points['Mixed_5c']
+    self.assertListEqual(pre_pool.get_shape().as_list(),
+                         [batch_size, 4, 4, 1024])
+
+  def testUnknownImageShape(self):
+    tf.reset_default_graph()
+    batch_size = 2
+    height, width = 224, 224
+    num_classes = 1000
+    input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
+    with self.test_session() as sess:
+      inputs = tf.placeholder(tf.float32, shape=(batch_size, None, None, 3))
+      logits, end_points = inception.inception_v2(inputs, num_classes)
+      self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
+      self.assertListEqual(logits.get_shape().as_list(),
+                           [batch_size, num_classes])
+      pre_pool = end_points['Mixed_5c']
+      feed_dict = {inputs: input_np}
+      tf.initialize_all_variables().run()
+      pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
+      self.assertListEqual(list(pre_pool_out.shape), [batch_size, 7, 7, 1024])
+
+  def testUnknowBatchSize(self):
+    batch_size = 1
+    height, width = 224, 224
+    num_classes = 1000
+
+    inputs = tf.placeholder(tf.float32, (None, height, width, 3))
+    logits, _ = inception.inception_v2(inputs, num_classes)
+    self.assertTrue(logits.op.name.startswith('InceptionV2/Logits'))
+    self.assertListEqual(logits.get_shape().as_list(),
+                         [None, num_classes])
+    images = tf.random_uniform((batch_size, height, width, 3))
+
+    with self.test_session() as sess:
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(logits, {inputs: images.eval()})
+      self.assertEquals(output.shape, (batch_size, num_classes))
+
+  def testEvaluation(self):
+    batch_size = 2
+    height, width = 224, 224
+    num_classes = 1000
+
+    eval_inputs = tf.random_uniform((batch_size, height, width, 3))
+    logits, _ = inception.inception_v2(eval_inputs, num_classes,
+                                       is_training=False)
+    predictions = tf.argmax(logits, 1)
+
+    with self.test_session() as sess:
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(predictions)
+      self.assertEquals(output.shape, (batch_size,))
+
+  def testTrainEvalWithReuse(self):
+    train_batch_size = 5
+    eval_batch_size = 2
+    height, width = 150, 150
+    num_classes = 1000
+
+    train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
+    inception.inception_v2(train_inputs, num_classes)
+    eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
+    logits, _ = inception.inception_v2(eval_inputs, num_classes, reuse=True)
+    predictions = tf.argmax(logits, 1)
+
+    with self.test_session() as sess:
+      sess.run(tf.initialize_all_variables())
+      output = sess.run(predictions)
+      self.assertEquals(output.shape, (eval_batch_size,))
+
+  def testLogitsNotSqueezed(self):
+    num_classes = 25
+    images = tf.random_uniform([1, 224, 224, 3])
+    logits, _ = inception.inception_v2(images,
+                                       num_classes=num_classes,
+                                       spatial_squeeze=False)
+
+    with self.test_session() as sess:
+      tf.initialize_all_variables().run()
+      logits_out = sess.run(logits)
+      self.assertListEqual(list(logits_out.shape), [1, 1, 1, num_classes])
+
+
+if __name__ == '__main__':
+  tf.test.main()

slim/nets/lenet.py

@@ -33,7 +33,8 @@ def lenet(images, num_classes=10, is_training=False,
   interval of (-infinity, infinity). Consequently, to convert the outputs to a
   probability distribution over the characters, one will need to convert them
   using the softmax function:
-        logits = mnist.Mnist(images, is_training=False)
+
+        logits = lenet.lenet(images, is_training=False)
         probabilities = tf.nn.softmax(logits)
         predictions = tf.argmax(logits, 1)
 

slim/nets/nets_factory.py

+# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+"""Contains a factory for building various models."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+import functools
+
+import tensorflow as tf
+
+from nets import alexnet
+from nets import cifarnet
+from nets import inception
+from nets import lenet
+from nets import overfeat
+from nets import resnet_v1
+from nets import resnet_v2
+from nets import vgg
+
+slim = tf.contrib.slim
+
+networks_map = {'alexnet_v2': alexnet.alexnet_v2,
+                'cifarnet': cifarnet.cifarnet,
+                'overfeat': overfeat.overfeat,
+                'vgg_a': vgg.vgg_a,
+                'vgg_16': vgg.vgg_16,
+                'vgg_19': vgg.vgg_19,
+                'inception_v1': inception.inception_v1,
+                'inception_v2': inception.inception_v2,
+                'inception_v3': inception.inception_v3,
+                'inception_resnet_v2': inception.inception_resnet_v2,
+                'lenet': lenet.lenet,
+                'resnet_v1_50': resnet_v1.resnet_v1_50,
+                'resnet_v1_101': resnet_v1.resnet_v1_101,
+                'resnet_v1_152': resnet_v1.resnet_v1_152,
+                'resnet_v1_200': resnet_v1.resnet_v1_200,
+                'resnet_v2_50': resnet_v2.resnet_v2_50,
+                'resnet_v2_101': resnet_v2.resnet_v2_101,
+                'resnet_v2_152': resnet_v2.resnet_v2_152,
+                'resnet_v2_200': resnet_v2.resnet_v2_200,
+               }
+
+arg_scopes_map = {'alexnet_v2': alexnet.alexnet_v2_arg_scope,
+                  'cifarnet': cifarnet.cifarnet_arg_scope,
+                  'overfeat': overfeat.overfeat_arg_scope,
+                  'vgg_a': vgg.vgg_arg_scope,
+                  'vgg_16': vgg.vgg_arg_scope,
+                  'vgg_19': vgg.vgg_arg_scope,
+                  'inception_v1': inception.inception_v3_arg_scope,
+                  'inception_v2': inception.inception_v3_arg_scope,
+                  'inception_v3': inception.inception_v3_arg_scope,
+                  'inception_resnet_v2':
+                  inception.inception_resnet_v2_arg_scope,
+                  'lenet': lenet.lenet_arg_scope,
+                  'resnet_v1_50': resnet_v1.resnet_arg_scope,
+                  'resnet_v1_101': resnet_v1.resnet_arg_scope,
+                  'resnet_v1_152': resnet_v1.resnet_arg_scope,
+                  'resnet_v1_200': resnet_v1.resnet_arg_scope,
+                  'resnet_v2_50': resnet_v2.resnet_arg_scope,
+                  'resnet_v2_101': resnet_v2.resnet_arg_scope,
+                  'resnet_v2_152': resnet_v2.resnet_arg_scope,
+                  'resnet_v2_200': resnet_v2.resnet_arg_scope,
+                 }
+
+
+def get_network_fn(name, num_classes, weight_decay=0.0, is_training=False):
+  """Returns a network_fn such as `logits, end_points = network_fn(images)`.
+
+  Args:
+    name: The name of the network.
+    num_classes: The number of classes to use for classification.
+    weight_decay: The l2 coefficient for the model weights.
+    is_training: `True` if the model is being used for training and `False`
+      otherwise.
+
+  Returns:
+    network_fn: A function that applies the model to a batch of images. It has
+      the following signature:
+        logits, end_points = network_fn(images)
+  Raises:
+    ValueError: If network `name` is not recognized.
+  """
+  if name not in networks_map:
+    raise ValueError('Name of network unknown %s' % name)
+  arg_scope = arg_scopes_map[name](weight_decay=weight_decay)
+  func = networks_map[name]
+  @functools.wraps(func)
+  def network_fn(images):
+    with slim.arg_scope(arg_scope):
+      return func(images, num_classes, is_training=is_training)
+  if hasattr(func, 'default_image_size'):
+    network_fn.default_image_size = func.default_image_size
+
+  return network_fn

slim/nets/nets_factory_test.py

+# Copyright 2016 Google Inc. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ==============================================================================
+
+"""Tests for slim.inception."""
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+
+import tensorflow as tf
+
+from nets import nets_factory
+
+
+class NetworksTest(tf.test.TestCase):
+
+  def testGetNetworkFn(self):
+    batch_size = 5
+    num_classes = 1000
+    for net in nets_factory.networks_map:
+      with self.test_session():
+        net_fn = nets_factory.get_network_fn(net, num_classes)
+        # Most networks use 224 as their default_image_size
+        image_size = getattr(net_fn, 'default_image_size', 224)
+        inputs = tf.random_uniform((batch_size, image_size, image_size, 3))
+        logits, end_points = net_fn(inputs)
+        self.assertTrue(isinstance(logits, tf.Tensor))
+        self.assertTrue(isinstance(end_points, dict))
+        self.assertEqual(logits.get_shape().as_list()[0], batch_size)
+        self.assertEqual(logits.get_shape().as_list()[-1], num_classes)
+
+if __name__ == '__main__':
+  tf.test.main()