Python tensorflow.contrib.slim.python.slim.nets.resnet_utils.conv2d_same() Examples

def build_base(self):
    with tf.variable_scope(self._resnet_scope, self._resnet_scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def testConv2DSameEven(self):
    n, n2 = 4, 2

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 26], [28, 48, 66, 37],
                                     [43, 66, 84, 46], [26, 37, 46, 22]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43], [43, 84]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = math_ops.to_float([[48, 37], [37, 22]])
    y4_expected = array_ops.reshape(y4_expected, [1, n2, n2, 1])

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def build_base(self):
    with tf.variable_scope(self._resnet_scope, self._resnet_scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def build_base(self):
        with tf.variable_scope(self.scope, self.scope):
            net = resnet_utils.conv2d_same(self.image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def build_base(self):
        with tf.variable_scope(self.scope, self.scope):
            net = resnet_utils.conv2d_same(self.image, 64, 7, stride=2, scope='conv1') # conv2d + subsample
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net

# Number of fixed blocks during training, by default ***the first of all 4 blocks*** is fixed (Resnet-50 block)
# Range: 0 (none) to 3 (all)
# __C.RESNET.FIXED_BLOCKS = 1

    # feature extractor 

def build_base(self):
        with tf.variable_scope(self.scope, self.scope):
            net = resnet_utils.conv2d_same(self.image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def build_base(self):
        with tf.variable_scope(self.scope, self.scope):
            net = resnet_utils.conv2d_same(self.image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def build_base(self):
        with tf.variable_scope(self.scope, self.scope):
            net = resnet_utils.conv2d_same(self.image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def _build_base(self):
    with tf.variable_scope(self._scope, self._scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def build_base(self):
    with tf.variable_scope(self._resnet_scope, self._resnet_scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def _build_base(self):
    with tf.variable_scope(self._scope, self._scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def testConv2DSameOdd(self):
    n, n2 = 5, 3

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 58, 34],
                                     [28, 48, 66, 84, 46],
                                     [43, 66, 84, 102, 55],
                                     [58, 84, 102, 120, 64],
                                     [34, 46, 55, 64, 30]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43, 34],
                                     [43, 84, 55],
                                     [34, 55, 30]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = y2_expected

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def _build_base(self):
    with tf.variable_scope(self._scope, self._scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def testConv2DSameEven(self):
    n, n2 = 4, 2

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 26], [28, 48, 66, 37],
                                     [43, 66, 84, 46], [26, 37, 46, 22]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43], [43, 84]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = math_ops.to_float([[48, 37], [37, 22]])
    y4_expected = array_ops.reshape(y4_expected, [1, n2, n2, 1])

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def build_base(self):
    with tf.variable_scope(self._resnet_scope, self._resnet_scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def testConv2DSameOdd(self):
    n, n2 = 5, 3

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46],
                                     [43, 66, 84, 102, 55],
                                     [58, 84, 102, 120, 64],
                                     [34, 46, 55, 64, 30]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = y2_expected

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def build_base(self):
    #with tf.variable_scope('noise'):
      ##kernel = tf.get_variable('weights',
                            #shape=[5, 5, 3, 3],
                            #initializer=tf.constant_initializer(Wcnn))
      #conv = tf.nn.conv2d(self.noise, Wcnn, [1, 1, 1, 1], padding='SAME',name='srm')
      #conv = tf.nn.conv2d(self.noise, kernel, [1, 1, 1, 1], padding='SAME',name='srm')
      #srm_conv = tf.nn.tanh(conv, name='tanh')
    with tf.variable_scope(self._resnet_scope, self._resnet_scope):
      net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
      net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
      net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

    return net 

def _build_base(self):
        with tf.variable_scope(self._resnet_scope):
            net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def _build_base(self):
        with tf.variable_scope(self._scope, self._scope):
            net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def _build_base(self):
        with tf.variable_scope(self._scope, self._scope):
            net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def _build_base(self):
        with tf.variable_scope(self._scope, self._scope):
            net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')
            net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])
            net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')

        return net 

def testConv2DSameOdd(self):
    n, n2 = 5, 3

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 58, 34], [28, 48, 66, 84, 46],
                                     [43, 66, 84, 102, 55],
                                     [58, 84, 102, 120, 64],
                                     [34, 46, 55, 64, 30]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43, 34], [43, 84, 55], [34, 55, 30]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = y2_expected

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def testConv2DSameEven(self):
    n, n2 = 4, 2

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 26], [28, 48, 66, 37],
                                     [43, 66, 84, 46], [26, 37, 46, 22]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43], [43, 84]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = math_ops.to_float([[48, 37], [37, 22]])
    y4_expected = array_ops.reshape(y4_expected, [1, n2, n2, 1])

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def testConv2DSameOdd(self):
    n, n2 = 5, 3

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 58, 34],
                                     [28, 48, 66, 84, 46],
                                     [43, 66, 84, 102, 55],
                                     [58, 84, 102, 120, 64],
                                     [34, 46, 55, 64, 30]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43, 34],
                                     [43, 84, 55],
                                     [34, 55, 30]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = y2_expected

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def testConv2DSameEven(self):
    n, n2 = 4, 2

    # Input image.
    x = create_test_input(1, n, n, 1)

    # Convolution kernel.
    w = create_test_input(1, 3, 3, 1)
    w = array_ops.reshape(w, [3, 3, 1, 1])

    variable_scope.get_variable('Conv/weights', initializer=w)
    variable_scope.get_variable('Conv/biases', initializer=array_ops.zeros([1]))
    variable_scope.get_variable_scope().reuse_variables()

    y1 = layers.conv2d(x, 1, [3, 3], stride=1, scope='Conv')
    y1_expected = math_ops.to_float([[14, 28, 43, 26], [28, 48, 66, 37],
                                     [43, 66, 84, 46], [26, 37, 46, 22]])
    y1_expected = array_ops.reshape(y1_expected, [1, n, n, 1])

    y2 = resnet_utils.subsample(y1, 2)
    y2_expected = math_ops.to_float([[14, 43], [43, 84]])
    y2_expected = array_ops.reshape(y2_expected, [1, n2, n2, 1])

    y3 = resnet_utils.conv2d_same(x, 1, 3, stride=2, scope='Conv')
    y3_expected = y2_expected

    y4 = layers.conv2d(x, 1, [3, 3], stride=2, scope='Conv')
    y4_expected = math_ops.to_float([[48, 37], [37, 22]])
    y4_expected = array_ops.reshape(y4_expected, [1, n2, n2, 1])

    with self.test_session() as sess:
      sess.run(variables.global_variables_initializer())
      self.assertAllClose(y1.eval(), y1_expected.eval())
      self.assertAllClose(y2.eval(), y2_expected.eval())
      self.assertAllClose(y3.eval(), y3_expected.eval())
      self.assertAllClose(y4.eval(), y4_expected.eval()) 

def resnet_v1_backbone(inputs,
              blocks,
              is_training=True,
              output_stride=None,
              include_root_block=True,
              reuse=None,
              scope=None):
  with variable_scope.variable_scope(
      scope, 'resnet_v1', [inputs], reuse=reuse) as sc:
    end_points_collection = sc.original_name_scope + '_end_points'
    with arg_scope(
        [layers.conv2d, bottleneck, resnet_utils.stack_blocks_dense],
        outputs_collections=end_points_collection):
      with arg_scope([layers.batch_norm], is_training=is_training):
        net = inputs
        if include_root_block:
          if output_stride is not None:
            if output_stride % 4 != 0:
              raise ValueError('The output_stride needs to be a multiple of 4.')
            output_stride /= 4
          net = resnet_utils.conv2d_same(net, 64, 7, stride=2, scope='conv1')
          net = layers_lib.max_pool2d(net, [3, 3], stride=2, scope='pool1')
        net = resnet_utils.stack_blocks_dense(net, blocks, output_stride)
        # Convert end_points_collection into a dictionary of end_points.
        end_points = utils.convert_collection_to_dict(end_points_collection)

        return net, end_points 

def atrous_spatial_pyramid_pooling(inputs, output_stride, batch_norm_decay, is_training, depth=256):
  """Atrous Spatial Pyramid Pooling.

  Args:
    inputs: A tensor of size [batch, height, width, channels].
    output_stride: The ResNet unit's stride. Determines the rates for atrous convolution.
      the rates are (6, 12, 18) when the stride is 16, and doubled when 8.
    batch_norm_decay: The moving average decay when estimating layer activation
      statistics in batch normalization.
    is_training: A boolean denoting whether the input is for training.
    depth: The depth of the ResNet unit output.

  Returns:
    The atrous spatial pyramid pooling output.
  """
  with tf.variable_scope("aspp"):
    if output_stride not in [8, 16]:
      raise ValueError('output_stride must be either 8 or 16.')

    atrous_rates = [6, 12, 18]
    if output_stride == 8:
      atrous_rates = [2*rate for rate in atrous_rates]

    with tf.contrib.slim.arg_scope(resnet_v2.resnet_arg_scope(batch_norm_decay=batch_norm_decay)):
      with arg_scope([layers.batch_norm], is_training=is_training):
        inputs_size = tf.shape(inputs)[1:3]
        # (a) one 1x1 convolution and three 3x3 convolutions with rates = (6, 12, 18) when output stride = 16.
        # the rates are doubled when output stride = 8.
        conv_1x1 = layers_lib.conv2d(inputs, depth, [1, 1], stride=1, scope="conv_1x1")
        conv_3x3_1 = resnet_utils.conv2d_same(inputs, depth, 3, stride=1, rate=atrous_rates[0], scope='conv_3x3_1')
        conv_3x3_2 = resnet_utils.conv2d_same(inputs, depth, 3, stride=1, rate=atrous_rates[1], scope='conv_3x3_2')
        conv_3x3_3 = resnet_utils.conv2d_same(inputs, depth, 3, stride=1, rate=atrous_rates[2], scope='conv_3x3_3')

        # (b) the image-level features
        with tf.variable_scope("image_level_features"):
          # global average pooling
          image_level_features = tf.reduce_mean(inputs, [1, 2], name='global_average_pooling', keepdims=True)
          # 1x1 convolution with 256 filters( and batch normalization)
          image_level_features = layers_lib.conv2d(image_level_features, depth, [1, 1], stride=1, scope='conv_1x1')
          # bilinearly upsample features
          image_level_features = tf.image.resize_bilinear(image_level_features, inputs_size, name='upsample')

        net = tf.concat([conv_1x1, conv_3x3_1, conv_3x3_2, conv_3x3_3, image_level_features], axis=3, name='concat')
        net = layers_lib.conv2d(net, depth, [1, 1], stride=1, scope='conv_1x1_concat')

        return net 

def conv2d_same(inputs, num_outputs, kernel_size, stride, rate=1, scope=None):
  """Strided 2-D convolution with 'SAME' padding.

  When stride > 1, then we do explicit zero-padding, followed by conv2d with
  'VALID' padding.

  Note that

     net = conv2d_same(inputs, num_outputs, 3, stride=stride)

  is equivalent to

     net = tf.contrib.layers.conv2d(inputs, num_outputs, 3, stride=1,
     padding='SAME')
     net = subsample(net, factor=stride)

  whereas

     net = tf.contrib.layers.conv2d(inputs, num_outputs, 3, stride=stride,
     padding='SAME')

  is different when the input's height or width is even, which is why we add the
  current function. For more details, see ResnetUtilsTest.testConv2DSameEven().

  Args:
    inputs: A 4-D tensor of size [batch, height_in, width_in, channels].
    num_outputs: An integer, the number of output filters.
    kernel_size: An int with the kernel_size of the filters.
    stride: An integer, the output stride.
    rate: An integer, rate for atrous convolution.
    scope: Scope.

  Returns:
    output: A 4-D tensor of size [batch, height_out, width_out, channels] with
      the convolution output.
  """
  if stride == 1:
    return layers_lib.conv2d(
        inputs,
        num_outputs,
        kernel_size,
        stride=1,
        rate=rate,
        padding='SAME',
        scope=scope)
  else:
    kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
    pad_total = kernel_size_effective - 1
    pad_beg = pad_total // 2
    pad_end = pad_total - pad_beg
    inputs = array_ops.pad(
        inputs, [[0, 0], [pad_beg, pad_end], [pad_beg, pad_end], [0, 0]])
    return layers_lib.conv2d(
        inputs,
        num_outputs,
        kernel_size,
        stride=stride,
        rate=rate,
        padding='VALID',
        scope=scope) 

def bottleneck(inputs,
               depth,
               depth_bottleneck,
               stride,
               rate=1,
               outputs_collections=None,
               scope=None):
  """Bottleneck residual unit variant with BN after convolutions.

  This is the original residual unit proposed in [1]. See Fig. 1(a) of [2] for
  its definition. Note that we use here the bottleneck variant which has an
  extra bottleneck layer.

  When putting together two consecutive ResNet blocks that use this unit, one
  should use stride = 2 in the last unit of the first block.

  Args:
    inputs: A tensor of size [batch, height, width, channels].
    depth: The depth of the ResNet unit output.
    depth_bottleneck: The depth of the bottleneck layers.
    stride: The ResNet unit's stride. Determines the amount of downsampling of
      the units output compared to its input.
    rate: An integer, rate for atrous convolution.
    outputs_collections: Collection to add the ResNet unit output.
    scope: Optional variable_scope.

  Returns:
    The ResNet unit's output.
  """
  with variable_scope.variable_scope(scope, 'bottleneck_v1', [inputs]) as sc:
    depth_in = utils.last_dimension(inputs.get_shape(), min_rank=4)
    if depth == depth_in:
      shortcut = resnet_utils.subsample(inputs, stride, 'shortcut')
    else:
      shortcut = layers.conv2d(
          inputs,
          depth, [1, 1],
          stride=stride,
          activation_fn=None,
          scope='shortcut')

    residual = layers.conv2d(
        inputs, depth_bottleneck, [1, 1], stride=1, scope='conv1')
    residual = resnet_utils.conv2d_same(
        residual, depth_bottleneck, 3, stride, rate=rate, scope='conv2')
    residual = layers.conv2d(
        residual, depth, [1, 1], stride=1, activation_fn=None, scope='conv3')

    output = nn_ops.relu(shortcut + residual)

    return utils.collect_named_outputs(outputs_collections, sc.name, output) 

def bottleneck(inputs,
               depth,
               depth_bottleneck,
               stride,
               rate=1,
               outputs_collections=None,
               scope=None):
  """Bottleneck residual unit variant with BN before convolutions.

  This is the full preactivation residual unit variant proposed in [2]. See
  Fig. 1(b) of [2] for its definition. Note that we use here the bottleneck
  variant which has an extra bottleneck layer.

  When putting together two consecutive ResNet blocks that use this unit, one
  should use stride = 2 in the last unit of the first block.

  Args:
    inputs: A tensor of size [batch, height, width, channels].
    depth: The depth of the ResNet unit output.
    depth_bottleneck: The depth of the bottleneck layers.
    stride: The ResNet unit's stride. Determines the amount of downsampling of
      the units output compared to its input.
    rate: An integer, rate for atrous convolution.
    outputs_collections: Collection to add the ResNet unit output.
    scope: Optional variable_scope.

  Returns:
    The ResNet unit's output.
  """
  with variable_scope.variable_scope(scope, 'bottleneck_v2', [inputs]) as sc:
    depth_in = utils.last_dimension(inputs.get_shape(), min_rank=4)
    preact = layers.batch_norm(
        inputs, activation_fn=nn_ops.relu, scope='preact')
    if depth == depth_in:
      shortcut = resnet_utils.subsample(inputs, stride, 'shortcut')
    else:
      shortcut = layers_lib.conv2d(
          preact,
          depth, [1, 1],
          stride=stride,
          normalizer_fn=None,
          activation_fn=None,
          scope='shortcut')

    residual = layers_lib.conv2d(
        preact, depth_bottleneck, [1, 1], stride=1, scope='conv1')
    residual = resnet_utils.conv2d_same(
        residual, depth_bottleneck, 3, stride, rate=rate, scope='conv2')
    residual = layers_lib.conv2d(
        residual,
        depth, [1, 1],
        stride=1,
        normalizer_fn=None,
        activation_fn=None,
        scope='conv3')

    output = shortcut + residual

    return utils.collect_named_outputs(outputs_collections, sc.name, output)