Add TF models slim nets

.gitignore

@@ -2,3 +2,4 @@
 .DS_Store
 my_*
 images/**/*.png
+*.pyc

nets/README.md

@@ -0,0 +1,5 @@
+This directory was copied from:
+https://github.com/tensorflow/models/blob/master/slim/nets
+
+On Sept. 25th, 2016. Commit:
+https://github.com/tensorflow/models/commit/65fad62dc6daca5a72c204013824cc380939d457

nets/__init__.py

@@ -0,0 +1 @@
+

nets/alexnet.py

@@ -0,0 +1,125 @@
+# 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

nets/alexnet_test.py

@@ -0,0 +1,145 @@
+# 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()

nets/cifarnet.py

@@ -0,0 +1,112 @@
+# 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