tf-faster-rcnn数据结构

subsample

def subsample(inputs, factor, scope=None):
  """Subsamples the input along the spatial dimensions.
  Args:
    inputs: A `Tensor` of size [batch, height_in, width_in, channels].
    factor: The subsampling factor.
    scope: Optional variable_scope.
  Returns:
    output: A `Tensor` of size [batch, height_out, width_out, channels] with the
      input, either intact (if factor == 1) or subsampled (if factor > 1).
  """
  if factor == 1:
    return inputs
  else:
    return slim.max_pool2d(inputs, [1, 1], stride=factor, scope=scope)

bottleneck

开始没理解resnet_utils.subsample和slim.conv2d的区别，后来发现其实
问题在于depth, 如何depth已经搞定了，那么就直接subsample就好了，如果
sample没搞定就得conv. 从这里可以看出一个问题desample的效果会好于conv2d.

def bottleneck(inputs, depth, depth_bottleneck, stride, rate=1,
               outputs_collections=None, scope=None):
 with tf.variable_scope(scope, 'bottleneck_v2', [inputs]) as sc:
    depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4)
    preact = slim.batch_norm(inputs, activation_fn=tf.nn.relu, scope='preact')
    if depth == depth_in:
      shortcut = resnet_utils.subsample(inputs, stride, 'shortcut')
    else:
      shortcut = slim.conv2d(preact, depth, [1, 1], stride=stride,
                             normalizer_fn=None, activation_fn=None,
                             scope='shortcut')

    residual = slim.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 = slim.conv2d(residual, depth, [1, 1], stride=1,
                           normalizer_fn=None, activation_fn=None,
                           scope='conv3')

    output = shortcut + residual

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