def testModelVariables(self):
     batch_size = 5
     height, width = 231, 231
     num_classes = 1000
     with self.test_session():
         inputs = tf.random_uniform((batch_size, height, width, 3))
         overfeat.overfeat(inputs, num_classes)
         expected_names = [
             'overfeat/conv1/weights',
             'overfeat/conv1/biases',
             'overfeat/conv2/weights',
             'overfeat/conv2/biases',
             'overfeat/conv3/weights',
             'overfeat/conv3/biases',
             'overfeat/conv4/weights',
             'overfeat/conv4/biases',
             'overfeat/conv5/weights',
             'overfeat/conv5/biases',
             'overfeat/fc6/weights',
             'overfeat/fc6/biases',
             'overfeat/fc7/weights',
             'overfeat/fc7/biases',
             'overfeat/fc8/weights',
             'overfeat/fc8/biases',
         ]
         model_variables = [v.op.name for v in slim.get_model_variables()]
         self.assertSetEqual(set(model_variables), set(expected_names))
 def testForward(self):
     batch_size = 1
     height, width = 231, 231
     with self.test_session() as sess:
         inputs = tf.random_uniform((batch_size, height, width, 3))
         logits, _ = overfeat.overfeat(inputs)
         sess.run(tf.global_variables_initializer())
         output = sess.run(logits)
         self.assertTrue(output.any())
 def testBuild(self):
     batch_size = 5
     height, width = 231, 231
     num_classes = 1000
     with self.test_session():
         inputs = tf.random_uniform((batch_size, height, width, 3))
         logits, _ = overfeat.overfeat(inputs, num_classes)
         self.assertEqual(logits.op.name, 'overfeat/fc8/squeezed')
         self.assertListEqual(logits.get_shape().as_list(),
                              [batch_size, num_classes])
 def testFullyConvolutional(self):
     batch_size = 1
     height, width = 281, 281
     num_classes = 1000
     with self.test_session():
         inputs = tf.random_uniform((batch_size, height, width, 3))
         logits, _ = overfeat.overfeat(inputs,
                                       num_classes,
                                       spatial_squeeze=False)
         self.assertEqual(logits.op.name, 'overfeat/fc8/BiasAdd')
         self.assertListEqual(logits.get_shape().as_list(),
                              [batch_size, 2, 2, num_classes])
 def testEvaluation(self):
     batch_size = 2
     height, width = 231, 231
     num_classes = 1000
     with self.test_session():
         eval_inputs = tf.random_uniform((batch_size, height, width, 3))
         logits, _ = overfeat.overfeat(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 testEndPoints(self):
     batch_size = 5
     height, width = 231, 231
     num_classes = 1000
     with self.test_session():
         inputs = tf.random_uniform((batch_size, height, width, 3))
         _, end_points = overfeat.overfeat(inputs, num_classes)
         expected_names = [
             'overfeat/conv1', 'overfeat/pool1', 'overfeat/conv2',
             'overfeat/pool2', 'overfeat/conv3', 'overfeat/conv4',
             'overfeat/conv5', 'overfeat/pool5', 'overfeat/fc6',
             'overfeat/fc7', 'overfeat/fc8'
         ]
         self.assertSetEqual(set(end_points.keys()), set(expected_names))
 def testNoClasses(self):
     batch_size = 5
     height, width = 231, 231
     num_classes = None
     with self.test_session():
         inputs = tf.random_uniform((batch_size, height, width, 3))
         net, end_points = overfeat.overfeat(inputs, num_classes)
         expected_names = [
             'overfeat/conv1', 'overfeat/pool1', 'overfeat/conv2',
             'overfeat/pool2', 'overfeat/conv3', 'overfeat/conv4',
             'overfeat/conv5', 'overfeat/pool5', 'overfeat/fc6',
             'overfeat/fc7'
         ]
         self.assertSetEqual(set(end_points.keys()), set(expected_names))
         self.assertTrue(net.op.name.startswith('overfeat/fc7'))
 def testTrainEvalWithReuse(self):
     train_batch_size = 2
     eval_batch_size = 1
     train_height, train_width = 231, 231
     eval_height, eval_width = 281, 281
     num_classes = 1000
     with self.test_session():
         train_inputs = tf.random_uniform(
             (train_batch_size, train_height, train_width, 3))
         logits, _ = overfeat.overfeat(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, _ = overfeat.overfeat(eval_inputs,
                                       is_training=False,
                                       spatial_squeeze=False)
         self.assertListEqual(logits.get_shape().as_list(),
                              [eval_batch_size, 2, 2, num_classes])
         logits = tf.reduce_mean(logits, [1, 2])
         predictions = tf.argmax(logits, 1)
         self.assertEqual(predictions.get_shape().as_list(),
                          [eval_batch_size])