Internal changes.

PiperOrigin-RevId: 303012385

official/vision/detection/configs/base_config.py

@@ -87,10 +87,6 @@ BASE_CFG = {
     },
     'resnet': {
         'resnet_depth': 50,
-        'dropblock': {
-            'dropblock_keep_prob': None,
-            'dropblock_size': None,
-        },
         'batch_norm': {
             'batch_norm_momentum': 0.997,
             'batch_norm_epsilon': 1e-4,
@@ -111,43 +107,6 @@ BASE_CFG = {
             'use_sync_bn': False,
         },
     },
-    'nasfpn': {
-        'min_level': 3,
-        'max_level': 7,
-        'fpn_feat_dims': 256,
-        'num_repeats': 5,
-        'use_separable_conv': False,
-        'dropblock': {
-            'dropblock_keep_prob': None,
-            'dropblock_size': None,
-        },
-        'batch_norm': {
-            'batch_norm_momentum': 0.997,
-            'batch_norm_epsilon': 1e-4,
-            'batch_norm_trainable': True,
-            'use_sync_bn': False,
-        },
-    },
-    # tunable_nasfpn:strip_begin
-    'tunable_nasfpn_v1': {
-        'min_level': 3,
-        'max_level': 7,
-        'fpn_feat_dims': 256,
-        'num_repeats': 5,
-        'use_separable_conv': False,
-        'dropblock': {
-            'dropblock_keep_prob': None,
-            'dropblock_size': None,
-        },
-        'batch_norm': {
-            'batch_norm_momentum': 0.997,
-            'batch_norm_epsilon': 1e-4,
-            'batch_norm_trainable': True,
-            'use_sync_bn': False,
-        },
-        'nodes': None
-    },
-    # tunable_nasfpn:strip_end
     'postprocess': {
         'use_batched_nms': False,
         'max_total_size': 100,

official/vision/detection/configs/retinanet_config.py

@@ -106,10 +106,6 @@ RETINANET_CFG = {
     },
     'resnet': {
         'resnet_depth': 50,
-        'dropblock': {
-            'dropblock_keep_prob': None,
-            'dropblock_size': None,
-        },
         'batch_norm': {
             'batch_norm_momentum': 0.997,
             'batch_norm_epsilon': 1e-4,
@@ -128,22 +124,6 @@ RETINANET_CFG = {
             'batch_norm_trainable': True,
         },
     },
-    'nasfpn': {
-        'min_level': 3,
-        'max_level': 7,
-        'fpn_feat_dims': 256,
-        'num_repeats': 5,
-        'use_separable_conv': False,
-        'dropblock': {
-            'dropblock_keep_prob': None,
-            'dropblock_size': None,
-        },
-        'batch_norm': {
-            'batch_norm_momentum': 0.997,
-            'batch_norm_epsilon': 1e-4,
-            'batch_norm_trainable': True,
-        },
-    },
     'retinanet_head': {
         'min_level': 3,
         'max_level': 7,

official/vision/detection/main.py

@@ -52,7 +52,7 @@ flags.DEFINE_string(
 
 flags.DEFINE_string(
     'model', default='retinanet',
-    help='Model to run: `retinanet` or `shapemask`.')
+    help='Model to run: `retinanet` or `mask_rcnn`.')
 
 flags.DEFINE_string('training_file_pattern', None,
                     'Location of the train data.')

official/vision/detection/modeling/architecture/factory.py

@@ -37,19 +37,12 @@ def batch_norm_relu_generator(params):
   return _batch_norm_op
 
 
-def dropblock_generator(params):
-  return nn_ops.Dropblock(
-      dropblock_keep_prob=params.dropblock_keep_prob,
-      dropblock_size=params.dropblock_size)
-
-
 def backbone_generator(params):
   """Generator function for various backbone models."""
   if params.architecture.backbone == 'resnet':
     resnet_params = params.resnet
     backbone_fn = resnet.Resnet(
         resnet_depth=resnet_params.resnet_depth,
-        dropblock=dropblock_generator(resnet_params.dropblock),
         batch_norm_relu=batch_norm_relu_generator(resnet_params.batch_norm))
   else:
     raise ValueError('Backbone model %s is not supported.' %

official/vision/detection/modeling/architecture/nn_ops.py

@@ -84,88 +84,3 @@ class BatchNormRelu(tf.keras.layers.Layer):
       inputs = tf.nn.relu(inputs)
     return inputs
 
-
-class Dropblock(object):
-  """DropBlock: a regularization method for convolutional neural networks.
-
-    DropBlock is a form of structured dropout, where units in a contiguous
-    region of a feature map are dropped together. DropBlock works better than
-    dropout on convolutional layers due to the fact that activation units in
-    convolutional layers are spatially correlated.
-    See https://arxiv.org/pdf/1810.12890.pdf for details.
-  """
-
-  def __init__(self,
-               dropblock_keep_prob=None,
-               dropblock_size=None,
-               data_format='channels_last'):
-    self._dropblock_keep_prob = dropblock_keep_prob
-    self._dropblock_size = dropblock_size
-    self._data_format = data_format
-
-  def __call__(self, net, is_training=False):
-    """Builds Dropblock layer.
-
-    Args:
-      net: `Tensor` input tensor.
-      is_training: `bool` if True, the model is in training mode.
-
-    Returns:
-      A version of input tensor with DropBlock applied.
-    """
-    if not is_training or self._dropblock_keep_prob is None:
-      return net
-
-    logging.info('Applying DropBlock: dropblock_size {}, net.shape {}'.format(
-        self._dropblock_size, net.shape))
-
-    if self._data_format == 'channels_last':
-      _, height, width, _ = net.get_shape().as_list()
-    else:
-      _, _, height, width = net.get_shape().as_list()
-
-    total_size = width * height
-    dropblock_size = min(self._dropblock_size, min(width, height))
-    # Seed_drop_rate is the gamma parameter of DropBlcok.
-    seed_drop_rate = (
-        1.0 - self._dropblock_keep_prob) * total_size / dropblock_size**2 / (
-            (width - self._dropblock_size + 1) *
-            (height - self._dropblock_size + 1))
-
-    # Forces the block to be inside the feature map.
-    w_i, h_i = tf.meshgrid(tf.range(width), tf.range(height))
-    valid_block = tf.logical_and(
-        tf.logical_and(w_i >= int(dropblock_size // 2),
-                       w_i < width - (dropblock_size - 1) // 2),
-        tf.logical_and(h_i >= int(dropblock_size // 2),
-                       h_i < width - (dropblock_size - 1) // 2))
-
-    if self._data_format == 'channels_last':
-      valid_block = tf.reshape(valid_block, [1, height, width, 1])
-    else:
-      valid_block = tf.reshape(valid_block, [1, 1, height, width])
-
-    randnoise = tf.random.uniform(net.shape, dtype=tf.float32)
-    valid_block = tf.cast(valid_block, dtype=tf.float32)
-    seed_keep_rate = tf.cast(1 - seed_drop_rate, dtype=tf.float32)
-    block_pattern = (1 - valid_block + seed_keep_rate + randnoise) >= 1
-    block_pattern = tf.cast(block_pattern, dtype=tf.float32)
-
-    if self._data_format == 'channels_last':
-      ksize = [1, self._dropblock_size, self._dropblock_size, 1]
-    else:
-      ksize = [1, 1, self._dropblock_size, self._dropblock_size]
-    block_pattern = -tf.nn.max_pool2d(
-        -block_pattern,
-        ksize=ksize,
-        strides=[1, 1, 1, 1],
-        padding='SAME',
-        data_format='NHWC' if self._data_format == 'channels_last' else 'NCHW')
-
-    percent_ones = tf.cast(
-        tf.reduce_sum(input_tensor=block_pattern), tf.float32) / tf.cast(
-            tf.size(input=block_pattern), tf.float32)
-
-    net = net / tf.cast(percent_ones, net.dtype) * tf.cast(
-        block_pattern, net.dtype)
-    return net

official/vision/detection/modeling/architecture/resnet.py

@@ -34,14 +34,12 @@ class Resnet(object):
 
   def __init__(self,
                resnet_depth,
-               dropblock=nn_ops.Dropblock(),
                batch_norm_relu=nn_ops.BatchNormRelu,
                data_format='channels_last'):
     """ResNet initialization function.
 
     Args:
       resnet_depth: `int` depth of ResNet backbone model.
-      dropblock: a dropblock layer.
       batch_norm_relu: an operation that includes a batch normalization layer
         followed by a relu layer(optional).
       data_format: `str` either "channels_first" for `[batch, channels, height,
@@ -49,7 +47,6 @@ class Resnet(object):
     """
     self._resnet_depth = resnet_depth
 
-    self._dropblock = dropblock
     self._batch_norm_relu = batch_norm_relu
 
     self._data_format = data_format
@@ -219,24 +216,20 @@ class Resnet(object):
           inputs=inputs, filters=filters_out, kernel_size=1, strides=strides)
       shortcut = self._batch_norm_relu(relu=False)(
           shortcut, is_training=is_training)
-    shortcut = self._dropblock(shortcut, is_training=is_training)
 
     inputs = self.conv2d_fixed_padding(
         inputs=inputs, filters=filters, kernel_size=1, strides=1)
     inputs = self._batch_norm_relu()(inputs, is_training=is_training)
-    inputs = self._dropblock(inputs, is_training=is_training)
 
     inputs = self.conv2d_fixed_padding(
         inputs=inputs, filters=filters, kernel_size=3, strides=strides)
     inputs = self._batch_norm_relu()(inputs, is_training=is_training)
-    inputs = self._dropblock(inputs, is_training=is_training)
 
     inputs = self.conv2d_fixed_padding(
         inputs=inputs, filters=4 * filters, kernel_size=1, strides=1)
     inputs = self._batch_norm_relu(
         relu=False, init_zero=True)(
             inputs, is_training=is_training)
-    inputs = self._dropblock(inputs, is_training=is_training)
 
     return tf.nn.relu(inputs + shortcut)