Diff for resnet model

resnet.diff

diff --git a/slim/nets/resnet_v1.py b/slim/nets/resnet_v1.py
index 03d49ed..edc2af9 100644
--- a/slim/nets/resnet_v1.py
+++ b/slim/nets/resnet_v1.py
@@ -226,7 +226,7 @@ def resnet_v1_50(inputs,
   return resnet_v1(inputs, blocks, num_classes, is_training,
                    global_pool=global_pool, output_stride=output_stride,
                    include_root_block=True, reuse=reuse, scope=scope)
-
+resnet_v1_50.default_image_size = resnet_v1.default_image_size
 
 def resnet_v1_101(inputs,
                   num_classes=None,
@@ -249,6 +249,7 @@ def resnet_v1_101(inputs,
   return resnet_v1(inputs, blocks, num_classes, is_training,
                    global_pool=global_pool, output_stride=output_stride,
                    include_root_block=True, reuse=reuse, scope=scope)
+resnet_v1_101.default_image_size = resnet_v1.default_image_size
 
 
 def resnet_v1_152(inputs,
diff --git a/slim/preprocessing/vgg_preprocessing.py b/slim/preprocessing/vgg_preprocessing.py
index 672c740..e226f89 100644
--- a/slim/preprocessing/vgg_preprocessing.py
+++ b/slim/preprocessing/vgg_preprocessing.py
@@ -73,7 +73,7 @@ def _crop(image, offset_height, offset_width, crop_height, crop_width):
       ['Rank of image must be equal to 3.'])
   cropped_shape = control_flow_ops.with_dependencies(
       [rank_assertion],
-      tf.pack([crop_height, crop_width, original_shape[2]]))
+      tf.stack([crop_height, crop_width, original_shape[2]]))
 
   size_assertion = tf.Assert(
       tf.logical_and(
@@ -81,7 +81,7 @@ def _crop(image, offset_height, offset_width, crop_height, crop_width):
           tf.greater_equal(original_shape[1], crop_width)),
       ['Crop size greater than the image size.'])
 
-  offsets = tf.to_int32(tf.pack([offset_height, offset_width, 0]))
+  offsets = tf.to_int32(tf.stack([offset_height, offset_width, 0]))
 
   # Use tf.slice instead of crop_to_bounding box as it accepts tensors to
   # define the crop size.
@@ -227,10 +227,10 @@ def _mean_image_subtraction(image, means):
   if len(means) != num_channels:
     raise ValueError('len(means) must match the number of channels')
 
-  channels = tf.split(2, num_channels, image)
+  channels = tf.split(image, num_channels, 2)
   for i in range(num_channels):
     channels[i] -= means[i]
-  return tf.concat(2, channels)
+  return tf.concat(channels, 2)
 
 
 def _smallest_size_at_least(height, width, smallest_side):