예제 #1
0
def nin(inputs,
        num_classes=10,
        is_training=True,
        restore_logits=True,
        scope=''):
  # end_points will collect relevant activations for external use, for example
  # summaries or losses.
  end_points = {}
  with tf.op_scope([inputs], scope, 'nin'):
    with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm],
                          is_training=is_training):
        # conv1
        end_points['conv1'] = ops.conv2d(inputs,192,[5,5],scope='conv1')
        end_points['conv1_1'] = ops.conv2d(end_points['conv1'],160,[1,1],scope='conv1_1')
        end_points['conv1_2'] = ops.conv2d(end_points['conv1_1'],96,[1,1],scope='conv1_2')
        end_points['pool1'] = ops.max_pool(end_points['conv1_2'],[3,3],stride=2,
                padding='SAME',scope='pool1')
        net = ops.dropout(end_points['pool1'],0.5)
        # conv2
        end_points['conv2'] = ops.conv2d(net,192,[5,5],scope='conv2')
        end_points['conv2_1'] = ops.conv2d(end_points['conv2'],192,[1,1],scope='conv2_1')
        end_points['conv2_2'] = ops.conv2d(end_points['conv2_1'],192,[1,1],scope='conv2_2')
        end_points['pool2'] = ops.max_pool(end_points['conv2_2'],[3,3],stride=2,
                padding='SAME',scope='pool2')
        net = ops.dropout(end_points['pool2'],0.5)
        # conv3
        end_points['conv3'] = ops.conv2d(net,192,[3,3],scope='conv3')
        end_points['conv3_1'] = ops.conv2d(end_points['conv3'],192,[1,1],scope='conv3_1')
        end_points['conv3_2'] = ops.conv2d(end_points['conv3_1'],10,[1,1],scope='conv3_2')
        net = ops.avg_pool(end_points['conv3_2'],[8,8],scope='avg_pool')
        flatten = ops.flatten(net,scope='flatten')
        #TODO take care this,using num_classes but 10..
        end_points['logits'] = ops.fc(flatten,num_classes,activation=None,scope='fc')

    return end_points['logits'],end_points
예제 #2
0
def nin_dssm(inputs,
        num_classes,
        num_of_exs,
        is_training=True,
        restore_logits=True,
        scope=''):
  # end_points will collect relevant activations for external use, for example
  # summaries or losses.
  end_points = {}
  with tf.op_scope([inputs], scope, 'nin'):
    with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm],
                          is_training=is_training):
        # conv1
        end_points['conv1'] = ops.conv2d(inputs,192,[5,5],scope='conv1')
        end_points['conv1_1'] = ops.conv2d(end_points['conv1'],160,[1,1],scope='conv1_1')
        end_points['conv1_2'] = ops.conv2d(end_points['conv1_1'],96,[1,1],scope='conv1_2')
        end_points['pool1'] = ops.max_pool(end_points['conv1_2'],[3,3],stride=2,
                padding='SAME',scope='pool1')
        net = ops.dropout(end_points['pool1'],0.5)
        # conv2 96*16*16
        end_points['conv2'] = ops.conv2d(net,192,[5,5],scope='conv2')
        end_points['conv2_1'] = ops.conv2d(end_points['conv2'],192,[1,1],scope='conv2_1')
        end_points['conv2_2'] = ops.conv2d(end_points['conv2_1'],192,[1,1],scope='conv2_2')
        end_points['pool2'] = ops.max_pool(end_points['conv2_2'],[3,3],stride=2,
                padding='SAME',scope='pool2')
        net = ops.dropout(end_points['pool2'],0.5)
        # conv3 192*8*8
        end_points['conv3'] = ops.conv2d(net,192,[3,3],scope='conv3')
        # 192 * 8 * 8
        end_points['conv3_1'] = ops.conv2d(end_points['conv3'],192,[1,1],scope='conv3_1')
        # 192 * 8 * 8
        #TODO using which layer feature?
        #firstly,consider conv3_1, and then consider fusion conv3 & conv3_1
        end_points['max_pool'] = ops.max_pool(end_points['conv3_1'],[8,8],scope='max_pool')
        end_points['avg_pool'] = ops.avg_pool(end_points['conv3_1'],[8,8],scope='avg_pool')
        end_points['hybrid_pool'] = 0.9*end_points['max_pool'] + 0.1*end_points['avg_pool']
        end_points['feature'] = tf.nn.l2_normalize(tf.squeeze(end_points['hybrid_pool']),dim=1)
        #OUTPUT (batch_size * num_negs_and_pos+1) * 192 ,eg. batch_size*3*192
        imgs = tf.split(0,num_of_exs ,end_points['feature'])
        anchors = imgs[0]
        positives = imgs[1]

        rst=[tf.reduce_sum(tf.mul(anchors,positives),1)]
        for k in xrange(2,num_of_exs):
            rst.append(tf.reduce_sum(tf.mul(anchors,imgs[k]),1))
        #batch*(negs-1)

        end_points['dssm'] = tf.concat(1,[tf.expand_dims(_,-1) for _ in rst])

        end_points['conv3_2'] = ops.conv2d(end_points['conv3_1'],10,[1,1],scope='conv3_2')
        net = ops.avg_pool(end_points['conv3_2'],[8,8],scope='avg_pool')
        flatten = ops.flatten(net,scope='flatten')
        #TODO take care this,using num_classes but 10..
        end_points['logits'] = ops.fc(flatten,num_classes,activation=None,scope='fc')

    return end_points['logits'],end_points['dssm'],end_points
예제 #3
0
 def testCreateDropout(self):
   height, width = 3, 3
   with self.test_session():
     images = tf.random_uniform((5, height, width, 3), seed=1)
     output = ops.dropout(images)
     self.assertEquals(output.op.name, 'Dropout/dropout/mul_1')
     output.get_shape().assert_is_compatible_with(images.get_shape())
예제 #4
0
 def testCreateDropout(self):
     height, width = 3, 3
     with self.test_session():
         images = tf.random_uniform((5, height, width, 3), seed=1)
         output = ops.dropout(images)
         self.assertEqual(output.op.name, 'Dropout/dropout/mul_1')
         output.get_shape().assert_is_compatible_with(images.get_shape())
 def testCreateDropoutNoTraining(self):
     height, width = 3, 3
     with self.test_session():
         images = tf.random_uniform(
             (5, height, width, 3), seed=1, name='images')
         output = ops.dropout(images, is_training=False)
         self.assertEquals(output, images)
예제 #6
0
 def testCreateDropoutNoTraining(self):
   height, width = 3, 3
   with self.test_session():
     images = tf.random_uniform((5, height, width, 3), seed=1, name='images')
     output = ops.dropout(images, is_training=False)
     self.assertEquals(output, images)
예제 #7
0
def inception_v3(inputs,
                 num_classes=2,
                 is_training=True,
                 dropout_keep_prob=0.8,
                 min_depth=16,
                 depth_multiplier=1.0,
                 spatial_squeeze=True,
                 reuse=None,
                 create_aux_logits=True,
                 scope='InceptionV3',
                 global_pool=False):
    """Inception model from http://arxiv.org/abs/1512.00567.

  "Rethinking the Inception Architecture for Computer Vision"

  Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
  Zbigniew Wojna.

  With the default arguments this method constructs the exact model defined in
  the paper. However, one can experiment with variations of the inception_v3
  network by changing arguments dropout_keep_prob, min_depth and
  depth_multiplier.

  The default image size used to train this network is 299x299.

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    num_classes: number of predicted classes. If 0 or None, the logits layer
      is omitted and the input features to the logits layer (before dropout)
      are returned instead.
    is_training: whether is training or not.
    dropout_keep_prob: the percentage of activation values that are retained.
    min_depth: Minimum depth value (number of channels) for all convolution ops.
      Enforced when depth_multiplier < 1, and not an active constraint when
      depth_multiplier >= 1.
    depth_multiplier: Float multiplier for the depth (number of channels)
      for all convolution ops. The value must be greater than zero. Typical
      usage will be to set this value in (0, 1) to reduce the number of
      parameters or computation cost of the model.
    prediction_fn: a function to get predictions out of logits.
    spatial_squeeze: if True, logits is of shape [B, C], if false logits is of
        shape [B, 1, 1, C], where B is batch_size and C is number of classes.
    reuse: whether or not the network and its variables should be reused. To be
      able to reuse 'scope' must be given.
    create_aux_logits: Whether to create the auxiliary logits.
    scope: Optional variable_scope.
    global_pool: Optional boolean flag to control the avgpooling before the
      logits layer. If false or unset, pooling is done with a fixed window
      that reduces default-sized inputs to 1x1, while larger inputs lead to
      larger outputs. If true, any input size is pooled down to 1x1.

  Returns:
    net: a Tensor with the logits (pre-softmax activations) if num_classes
      is a non-zero integer, or the non-dropped-out input to the logits layer
      if num_classes is 0 or None.
    end_points: a dictionary from components of the network to the corresponding
      activation.

  Raises:
    ValueError: if 'depth_multiplier' is less than or equal to zero.
  """
    if depth_multiplier <= 0:
        raise ValueError('depth_multiplier is not greater than zero.')
    depth = lambda d: max(int(d * depth_multiplier), min_depth)
    #with tf.variable_scope(scope, 'InceptionV3', [inputs], reuse=reuse) as scope:
    with tf.name_scope(scope, 'inception_v3', [inputs]) as scope:
        with scopes.arg_scope([ops.batch_norm, ops.dropout],
                              is_training=is_training):
            net, end_points = inception_v3_base(
                inputs,
                scope=scope,
                min_depth=min_depth,
                depth_multiplier=depth_multiplier,
                is_training=is_training)

            # Auxiliary Head logits
            if create_aux_logits and num_classes:
                with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                                      stride=1,
                                      padding='SAME'):

                    aux_logits = tf.identity(end_points['Mixed_6e'])
                    with tf.variable_scope('aux_logits'):
                        aux_logits = ops.avg_pool(aux_logits, [5, 5],
                                                  stride=3,
                                                  padding='VALID')
                        aux_logits = ops.conv2d(aux_logits,
                                                128, [1, 1],
                                                scope='proj')
                        # Shape of feature map before the final layer.
                        shape = aux_logits.get_shape()
                        aux_logits = ops.conv2d(aux_logits,
                                                768,
                                                shape[1:3],
                                                stddev=0.01,
                                                padding='VALID')
                        aux_logits = ops.flatten(aux_logits)
                        aux_logits = ops.fc(aux_logits,
                                            num_classes,
                                            activation=None,
                                            stddev=0.001,
                                            restore=reuse)
                        end_points['aux_logits'] = aux_logits

            with tf.variable_scope('logits'):
                shape = net.get_shape()
                net = ops.avg_pool(net,
                                   shape[1:3],
                                   padding='VALID',
                                   scope='pool')
                # 1 x 1 x 2048
                net = ops.dropout(net, dropout_keep_prob, scope='dropout')
                net = ops.flatten(net, scope='flatten')
                # 2048
                logits = ops.fc(net,
                                num_classes,
                                activation=None,
                                scope='logits',
                                restore=reuse)
                # 1000
                end_points['logits'] = logits
                end_points['predictions'] = tf.nn.softmax(logits,
                                                          name='predictions')

    return net, logits, end_points
예제 #8
0
def inception_v3(inputs,
                 dropout_keep_prob=0.8,
                 num_classes=1000,
                 is_training=True,
                 restore_logits=True,
                 scope=''):
    """Latest Inception from http://arxiv.org/abs/1512.00567.

    "Rethinking the Inception Architecture for Computer Vision"

    Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
    Zbigniew Wojna

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    dropout_keep_prob: dropout keep_prob.
    num_classes: number of predicted classes.
    is_training: whether is training or not.
    restore_logits: whether or not the logits layers should be restored.
      Useful for fine-tuning a model with different num_classes.
    scope: Optional scope for name_scope.

  Returns:
    a list containing 'logits', 'aux_logits' Tensors.
  """
    # end_points will collect relevant activations for external use, for example
    # summaries or losses.
    end_points = {}
    with tf.name_scope(scope, 'inception_v3', [inputs]):
        with scopes.arg_scope(
            [ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
                is_training=is_training):
            with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                                  stride=1,
                                  padding='VALID'):
                # 299 x 299 x 3
                end_points['conv0'] = ops.conv2d(inputs,
                                                 32, [3, 3],
                                                 stride=2,
                                                 scope='conv0')
                # 149 x 149 x 32
                end_points['conv1'] = ops.conv2d(end_points['conv0'],
                                                 32, [3, 3],
                                                 scope='conv1')
                # 147 x 147 x 32
                end_points['conv2'] = ops.conv2d(end_points['conv1'],
                                                 64, [3, 3],
                                                 padding='SAME',
                                                 scope='conv2')
                # 147 x 147 x 64
                end_points['pool1'] = ops.max_pool(end_points['conv2'], [3, 3],
                                                   stride=2,
                                                   scope='pool1')
                # 73 x 73 x 64
                end_points['conv3'] = ops.conv2d(end_points['pool1'],
                                                 80, [1, 1],
                                                 scope='conv3')
                # 73 x 73 x 80.
                end_points['conv4'] = ops.conv2d(end_points['conv3'],
                                                 192, [3, 3],
                                                 scope='conv4')
                # 71 x 71 x 192.
                end_points['pool2'] = ops.max_pool(end_points['conv4'], [3, 3],
                                                   stride=2,
                                                   scope='pool2')
                # 35 x 35 x 192.
                net = end_points['pool2']
            # Inception blocks
            with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                                  stride=1,
                                  padding='SAME'):
                # mixed: 35 x 35 x 256.
                with tf.variable_scope('mixed_35x35x256a'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 64, [1, 1])
                    with tf.variable_scope('branch5x5'):
                        branch5x5 = ops.conv2d(net, 48, [1, 1])
                        branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 32, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch5x5, branch3x3dbl, branch_pool], 3)
                    end_points['mixed_35x35x256a'] = net
                # mixed_1: 35 x 35 x 288.
                with tf.variable_scope('mixed_35x35x288a'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 64, [1, 1])
                    with tf.variable_scope('branch5x5'):
                        branch5x5 = ops.conv2d(net, 48, [1, 1])
                        branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch5x5, branch3x3dbl, branch_pool], 3)
                    end_points['mixed_35x35x288a'] = net
                # mixed_2: 35 x 35 x 288.
                with tf.variable_scope('mixed_35x35x288b'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 64, [1, 1])
                    with tf.variable_scope('branch5x5'):
                        branch5x5 = ops.conv2d(net, 48, [1, 1])
                        branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch5x5, branch3x3dbl, branch_pool], 3)
                    end_points['mixed_35x35x288b'] = net
                # mixed_3: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768a'):
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net,
                                               384, [3, 3],
                                               stride=2,
                                               padding='VALID')
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl,
                                                  96, [3, 3],
                                                  stride=2,
                                                  padding='VALID')
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.max_pool(net, [3, 3],
                                                   stride=2,
                                                   padding='VALID')
                    net = tf.concat([branch3x3, branch3x3dbl, branch_pool], 3)
                    end_points['mixed_17x17x768a'] = net
                # mixed4: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768b'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 128, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 128, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 128, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
                    end_points['mixed_17x17x768b'] = net
                # mixed_5: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768c'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 160, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 160, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
                    end_points['mixed_17x17x768c'] = net
                # mixed_6: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768d'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 160, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 160, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
                    end_points['mixed_17x17x768d'] = net
                # mixed_7: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768e'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 192, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 192, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 192, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
                    end_points['mixed_17x17x768e'] = net
                # Auxiliary Head logits
                aux_logits = tf.identity(end_points['mixed_17x17x768e'])
                with tf.variable_scope('aux_logits'):
                    aux_logits = ops.avg_pool(aux_logits, [5, 5],
                                              stride=3,
                                              padding='VALID')
                    aux_logits = ops.conv2d(aux_logits,
                                            128, [1, 1],
                                            scope='proj')
                    # Shape of feature map before the final layer.
                    shape = aux_logits.get_shape()
                    aux_logits = ops.conv2d(aux_logits,
                                            768,
                                            shape[1:3],
                                            stddev=0.01,
                                            padding='VALID')
                    aux_logits = ops.flatten(aux_logits)
                    aux_logits = ops.fc(aux_logits,
                                        num_classes,
                                        activation=None,
                                        stddev=0.001,
                                        restore=restore_logits)
                    end_points['aux_logits'] = aux_logits
                # mixed_8: 8 x 8 x 1280.
                # Note that the scope below is not changed to not void previous
                # checkpoints.
                # (TODO) Fix the scope when appropriate.
                with tf.variable_scope('mixed_17x17x1280a'):
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net, 192, [1, 1])
                        branch3x3 = ops.conv2d(branch3x3,
                                               320, [3, 3],
                                               stride=2,
                                               padding='VALID')
                    with tf.variable_scope('branch7x7x3'):
                        branch7x7x3 = ops.conv2d(net, 192, [1, 1])
                        branch7x7x3 = ops.conv2d(branch7x7x3, 192, [1, 7])
                        branch7x7x3 = ops.conv2d(branch7x7x3, 192, [7, 1])
                        branch7x7x3 = ops.conv2d(branch7x7x3,
                                                 192, [3, 3],
                                                 stride=2,
                                                 padding='VALID')
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.max_pool(net, [3, 3],
                                                   stride=2,
                                                   padding='VALID')
                    net = tf.concat([branch3x3, branch7x7x3, branch_pool], 3)
                    end_points['mixed_17x17x1280a'] = net
                # mixed_9: 8 x 8 x 2048.
                with tf.variable_scope('mixed_8x8x2048a'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 320, [1, 1])
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net, 384, [1, 1])
                        branch3x3 = tf.concat([
                            ops.conv2d(branch3x3, 384, [1, 3]),
                            ops.conv2d(branch3x3, 384, [3, 1])
                        ], 3)
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 448, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
                        branch3x3dbl = tf.concat([
                            ops.conv2d(branch3x3dbl, 384, [1, 3]),
                            ops.conv2d(branch3x3dbl, 384, [3, 1])
                        ], 3)
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch3x3, branch3x3dbl, branch_pool], 3)
                    end_points['mixed_8x8x2048a'] = net
                # mixed_10: 8 x 8 x 2048.
                with tf.variable_scope('mixed_8x8x2048b'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 320, [1, 1])
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net, 384, [1, 1])
                        branch3x3 = tf.concat([
                            ops.conv2d(branch3x3, 384, [1, 3]),
                            ops.conv2d(branch3x3, 384, [3, 1])
                        ], 3)
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 448, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
                        branch3x3dbl = tf.concat([
                            ops.conv2d(branch3x3dbl, 384, [1, 3]),
                            ops.conv2d(branch3x3dbl, 384, [3, 1])
                        ], 3)
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(
                        [branch1x1, branch3x3, branch3x3dbl, branch_pool], 3)
                    end_points['mixed_8x8x2048b'] = net
                # Final pooling and prediction
                with tf.variable_scope('logits'):
                    shape = net.get_shape()
                    net = ops.avg_pool(net,
                                       shape[1:3],
                                       padding='VALID',
                                       scope='pool')
                    # 1 x 1 x 2048
                    net = ops.dropout(net, dropout_keep_prob, scope='dropout')
                    net = ops.flatten(net, scope='flatten')
                    # 2048
                    logits_2048 = net
                    logits = ops.fc(net,
                                    num_classes,
                                    activation=None,
                                    scope='logits',
                                    restore=restore_logits)
                    # 1000
                    end_points['logits'] = logits
                    end_points['predictions'] = tf.nn.softmax(
                        logits, name='predictions')
            return logits, end_points, logits_2048
예제 #9
0
def vgg(inputs,
        num_classes=1000,
        is_training=True,
        restore_logits=True,
        scope=''):
    # end_points will collect relevant activations for external use, for example
    # summaries or losses.
    end_points = {}
    with tf.op_scope([inputs], scope, 'vgg'):
        with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm],
                              is_training=is_training):
            # conv1
            end_points['conv1'] = ops.repeat_op(2,
                                                inputs,
                                                ops.conv2d,
                                                64, [3, 3],
                                                scope='conv1')
            end_points['pool1'] = ops.max_pool(end_points['conv1'], [2, 2],
                                               scope='pool1')
            # conv2
            end_points['conv2'] = ops.repeat_op(2,
                                                end_points['pool1'],
                                                ops.conv2d,
                                                128, [3, 3],
                                                scope='conv2')
            end_points['pool2'] = ops.max_pool(end_points['conv2'], [2, 2],
                                               scope='pool2')
            # conv3
            end_points['conv3'] = ops.repeat_op(2,
                                                end_points['pool2'],
                                                ops.conv2d,
                                                256, [3, 3],
                                                scope='conv3')
            end_points['pool3'] = ops.max_pool(end_points['conv3'], [2, 2],
                                               scope='pool3')
            # conv4
            end_points['conv4'] = ops.repeat_op(2,
                                                end_points['pool3'],
                                                ops.conv2d,
                                                512, [3, 3],
                                                scope='conv4')
            end_points['pool4'] = ops.max_pool(end_points['conv4'], [2, 2],
                                               scope='pool4')
            # conv5
            end_points['conv5'] = ops.repeat_op(2,
                                                end_points['pool4'],
                                                ops.conv2d,
                                                512, [3, 3],
                                                scope='conv5')
            end_points['pool5'] = ops.max_pool(end_points['conv5'], [2, 2],
                                               scope='pool5')

            end_points['flatten5'] = ops.flatten(end_points['pool5'],
                                                 scope='flatten5')
            end_points['fc6'] = ops.fc(end_points['flatten5'],
                                       4096,
                                       scope='fc6')
            end_points['dropout6'] = ops.dropout(end_points['fc6'],
                                                 0.5,
                                                 scope='dropout6')
            end_points['fc7'] = ops.fc(end_points['dropout6'],
                                       4096,
                                       scope='fc7')
            end_points['dropout7'] = ops.dropout(end_points['fc7'],
                                                 0.5,
                                                 scope='dropout7')

            logits = ops.fc(end_points['fc7'],
                            num_classes,
                            activation=None,
                            scope='fc8')
        return logits, end_points
예제 #10
0
def inception_v3(inputs,
                 dropout_keep_prob=0.8,
                 num_classes=1000,
                 is_training=True,
                 restore_logits=True,
                 scope=''):

    # end_points will collect relevant activations for external use, for example
    # summaries or losses.
    end_points = {}
    with tf.name_scope(scope, 'inception_v3', [inputs]):
        with scopes.arg_scope(
            [ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
                is_training=is_training):
            with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                                  stride=1,
                                  padding='VALID'):
                # 299 x 299 x 3
                end_points['conv0'] = ops.conv2d(inputs,
                                                 32, [3, 3],
                                                 stride=2,
                                                 scope='conv0')
                # 149 x 149 x 32
                end_points['conv1'] = ops.conv2d(end_points['conv0'],
                                                 32, [3, 3],
                                                 scope='conv1')
                # 147 x 147 x 32
                end_points['conv2'] = ops.conv2d(end_points['conv1'],
                                                 64, [3, 3],
                                                 padding='SAME',
                                                 scope='conv2')
                # 147 x 147 x 64
                end_points['pool1'] = ops.max_pool(end_points['conv2'], [3, 3],
                                                   stride=2,
                                                   scope='pool1')
                # 73 x 73 x 64
                end_points['conv3'] = ops.conv2d(end_points['pool1'],
                                                 80, [1, 1],
                                                 scope='conv3')
                # 73 x 73 x 80.
                end_points['conv4'] = ops.conv2d(end_points['conv3'],
                                                 192, [3, 3],
                                                 scope='conv4')
                # 71 x 71 x 192.
                end_points['pool2'] = ops.max_pool(end_points['conv4'], [3, 3],
                                                   stride=2,
                                                   scope='pool2')
                # 35 x 35 x 192.
                net = end_points['pool2']
            # Inception blocks
            with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                                  stride=1,
                                  padding='SAME'):
                # mixed: 35 x 35 x 256.
                with tf.variable_scope('mixed_35x35x256a'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 64, [1, 1])
                    with tf.variable_scope('branch5x5'):
                        branch5x5 = ops.conv2d(net, 48, [1, 1])
                        branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 32, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch5x5, branch3x3dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_35x35x256a'] = net
                # mixed_1: 35 x 35 x 288.
                with tf.variable_scope('mixed_35x35x288a'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 64, [1, 1])
                    with tf.variable_scope('branch5x5'):
                        branch5x5 = ops.conv2d(net, 48, [1, 1])
                        branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch5x5, branch3x3dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_35x35x288a'] = net
                # mixed_2: 35 x 35 x 288.
                with tf.variable_scope('mixed_35x35x288b'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 64, [1, 1])
                    with tf.variable_scope('branch5x5'):
                        branch5x5 = ops.conv2d(net, 48, [1, 1])
                        branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch5x5, branch3x3dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_35x35x288b'] = net
                # mixed_3: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768a'):
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net,
                                               384, [3, 3],
                                               stride=2,
                                               padding='VALID')
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 64, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
                        branch3x3dbl = ops.conv2d(branch3x3dbl,
                                                  96, [3, 3],
                                                  stride=2,
                                                  padding='VALID')
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.max_pool(net, [3, 3],
                                                   stride=2,
                                                   padding='VALID')
                    net = tf.concat(
                        axis=3, values=[branch3x3, branch3x3dbl, branch_pool])
                    end_points['mixed_17x17x768a'] = net
                # mixed4: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768b'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 128, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 128, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 128, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch7x7, branch7x7dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_17x17x768b'] = net
                # mixed_5: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768c'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 160, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 160, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch7x7, branch7x7dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_17x17x768c'] = net
                # mixed_6: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768d'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 160, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 160, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch7x7, branch7x7dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_17x17x768d'] = net
                # mixed_7: 17 x 17 x 768.
                with tf.variable_scope('mixed_17x17x768e'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 192, [1, 1])
                    with tf.variable_scope('branch7x7'):
                        branch7x7 = ops.conv2d(net, 192, [1, 1])
                        branch7x7 = ops.conv2d(branch7x7, 192, [1, 7])
                        branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
                    with tf.variable_scope('branch7x7dbl'):
                        branch7x7dbl = ops.conv2d(net, 192, [1, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
                        branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch7x7, branch7x7dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_17x17x768e'] = net
                # Auxiliary Head logits
                aux_logits = tf.identity(end_points['mixed_17x17x768e'])
                with tf.variable_scope('aux_logits'):
                    aux_logits = ops.avg_pool(aux_logits, [5, 5],
                                              stride=3,
                                              padding='VALID')
                    aux_logits = ops.conv2d(aux_logits,
                                            128, [1, 1],
                                            scope='proj')
                    # Shape of feature map before the final layer.
                    shape = aux_logits.get_shape()
                    aux_logits = ops.conv2d(aux_logits,
                                            768,
                                            shape[1:3],
                                            stddev=0.01,
                                            padding='VALID')
                    aux_logits = ops.flatten(aux_logits)
                    aux_logits = ops.fc(aux_logits,
                                        num_classes,
                                        activation=None,
                                        stddev=0.001,
                                        restore=restore_logits)
                    end_points['aux_logits'] = aux_logits
                # mixed_8: 8 x 8 x 1280.
                # Note that the scope below is not changed to not void previous
                # checkpoints.
                # (TODO) Fix the scope when appropriate.
                with tf.variable_scope('mixed_17x17x1280a'):
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net, 192, [1, 1])
                        branch3x3 = ops.conv2d(branch3x3,
                                               320, [3, 3],
                                               stride=2,
                                               padding='VALID')
                    with tf.variable_scope('branch7x7x3'):
                        branch7x7x3 = ops.conv2d(net, 192, [1, 1])
                        branch7x7x3 = ops.conv2d(branch7x7x3, 192, [1, 7])
                        branch7x7x3 = ops.conv2d(branch7x7x3, 192, [7, 1])
                        branch7x7x3 = ops.conv2d(branch7x7x3,
                                                 192, [3, 3],
                                                 stride=2,
                                                 padding='VALID')
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.max_pool(net, [3, 3],
                                                   stride=2,
                                                   padding='VALID')
                    net = tf.concat(
                        axis=3, values=[branch3x3, branch7x7x3, branch_pool])
                    end_points['mixed_17x17x1280a'] = net
                # mixed_9: 8 x 8 x 2048.
                with tf.variable_scope('mixed_8x8x2048a'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 320, [1, 1])
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net, 384, [1, 1])
                        branch3x3 = tf.concat(
                            axis=3,
                            values=[
                                ops.conv2d(branch3x3, 384, [1, 3]),
                                ops.conv2d(branch3x3, 384, [3, 1])
                            ])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 448, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
                        branch3x3dbl = tf.concat(
                            axis=3,
                            values=[
                                ops.conv2d(branch3x3dbl, 384, [1, 3]),
                                ops.conv2d(branch3x3dbl, 384, [3, 1])
                            ])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch3x3, branch3x3dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_8x8x2048a'] = net
                # mixed_10: 8 x 8 x 2048.
                with tf.variable_scope('mixed_8x8x2048b'):
                    with tf.variable_scope('branch1x1'):
                        branch1x1 = ops.conv2d(net, 320, [1, 1])
                    with tf.variable_scope('branch3x3'):
                        branch3x3 = ops.conv2d(net, 384, [1, 1])
                        branch3x3 = tf.concat(
                            axis=3,
                            values=[
                                ops.conv2d(branch3x3, 384, [1, 3]),
                                ops.conv2d(branch3x3, 384, [3, 1])
                            ])
                    with tf.variable_scope('branch3x3dbl'):
                        branch3x3dbl = ops.conv2d(net, 448, [1, 1])
                        branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
                        branch3x3dbl = tf.concat(
                            axis=3,
                            values=[
                                ops.conv2d(branch3x3dbl, 384, [1, 3]),
                                ops.conv2d(branch3x3dbl, 384, [3, 1])
                            ])
                    with tf.variable_scope('branch_pool'):
                        branch_pool = ops.avg_pool(net, [3, 3])
                        branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
                    net = tf.concat(axis=3,
                                    values=[
                                        branch1x1, branch3x3, branch3x3dbl,
                                        branch_pool
                                    ])
                    end_points['mixed_8x8x2048b'] = net
                # Final pooling and prediction
                with tf.variable_scope('logits'):
                    shape = net.get_shape()
                    net = ops.avg_pool(net,
                                       shape[1:3],
                                       padding='VALID',
                                       scope='pool')
                    # 1 x 1 x 2048
                    net = ops.dropout(net, dropout_keep_prob, scope='dropout')
                    net = ops.flatten(net, scope='flatten')
                    # 2048
                    logits = ops.fc(net,
                                    num_classes,
                                    activation=None,
                                    scope='logits',
                                    restore=restore_logits)
                    # 1000
                    end_points['logits'] = logits
                    end_points['predictions'] = tf.nn.softmax(
                        logits, name='predictions')
            return logits, end_points
예제 #11
0
def inception_v3(inputs,
                 dropout_keep_prob=0.8,
                 num_classes=1000,
                 is_training=True,
                 restore_logits=True,
                 scope=''):
  """Latest Inception from http://arxiv.org/abs/1512.00567.

    "Rethinking the Inception Architecture for Computer Vision"

    Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
    Zbigniew Wojna

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    dropout_keep_prob: dropout keep_prob.
    num_classes: number of predicted classes.
    is_training: whether is training or not.
    restore_logits: whether or not the logits layers should be restored.
      Useful for fine-tuning a model with different num_classes.
    scope: Optional scope for name_scope.

  Returns:
    a list containing 'logits', 'aux_logits' Tensors.
  """
  # end_points will collect relevant activations for external use, for example
  # summaries or losses.
  end_points = {}
  with tf.name_scope(scope, 'inception_v3', [inputs]):
    with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
                          is_training=is_training):
      with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                            stride=1, padding='VALID'):
        # 299 x 299 x 3
        end_points['conv0'] = ops.conv2d(inputs, 32, [3, 3], stride=2,
                                         scope='conv0')
        # 149 x 149 x 32
        end_points['conv1'] = ops.conv2d(end_points['conv0'], 32, [3, 3],
                                         scope='conv1')
        # 147 x 147 x 32
        end_points['conv2'] = ops.conv2d(end_points['conv1'], 64, [3, 3],
                                         padding='SAME', scope='conv2')
        # 147 x 147 x 64
        end_points['pool1'] = ops.max_pool(end_points['conv2'], [3, 3],
                                           stride=2, scope='pool1')
        # 73 x 73 x 64
        end_points['conv3'] = ops.conv2d(end_points['pool1'], 80, [1, 1],
                                         scope='conv3')
        # 73 x 73 x 80.
        end_points['conv4'] = ops.conv2d(end_points['conv3'], 192, [3, 3],
                                         scope='conv4')
        # 71 x 71 x 192.
        end_points['pool2'] = ops.max_pool(end_points['conv4'], [3, 3],
                                           stride=2, scope='pool2')
        # 35 x 35 x 192.
        net = end_points['pool2']
      # Inception blocks
      with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                            stride=1, padding='SAME'):
        # mixed: 35 x 35 x 256.
        with tf.variable_scope('mixed_35x35x256a'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 64, [1, 1])
          with tf.variable_scope('branch5x5'):
            branch5x5 = ops.conv2d(net, 48, [1, 1])
            branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
          with tf.variable_scope('branch3x3dbl'):
            branch3x3dbl = ops.conv2d(net, 64, [1, 1])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 32, [1, 1])
          net = tf.concat([branch1x1, branch5x5, branch3x3dbl, branch_pool], 3)
          end_points['mixed_35x35x256a'] = net
        # mixed_1: 35 x 35 x 288.
        with tf.variable_scope('mixed_35x35x288a'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 64, [1, 1])
          with tf.variable_scope('branch5x5'):
            branch5x5 = ops.conv2d(net, 48, [1, 1])
            branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
          with tf.variable_scope('branch3x3dbl'):
            branch3x3dbl = ops.conv2d(net, 64, [1, 1])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
          net = tf.concat([branch1x1, branch5x5, branch3x3dbl, branch_pool], 3)
          end_points['mixed_35x35x288a'] = net
        # mixed_2: 35 x 35 x 288.
        with tf.variable_scope('mixed_35x35x288b'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 64, [1, 1])
          with tf.variable_scope('branch5x5'):
            branch5x5 = ops.conv2d(net, 48, [1, 1])
            branch5x5 = ops.conv2d(branch5x5, 64, [5, 5])
          with tf.variable_scope('branch3x3dbl'):
            branch3x3dbl = ops.conv2d(net, 64, [1, 1])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 64, [1, 1])
          net = tf.concat([branch1x1, branch5x5, branch3x3dbl, branch_pool], 3)
          end_points['mixed_35x35x288b'] = net
        # mixed_3: 17 x 17 x 768.
        with tf.variable_scope('mixed_17x17x768a'):
          with tf.variable_scope('branch3x3'):
            branch3x3 = ops.conv2d(net, 384, [3, 3], stride=2, padding='VALID')
          with tf.variable_scope('branch3x3dbl'):
            branch3x3dbl = ops.conv2d(net, 64, [1, 1])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 96, [3, 3],
                                      stride=2, padding='VALID')
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.max_pool(net, [3, 3], stride=2, padding='VALID')
          net = tf.concat([branch3x3, branch3x3dbl, branch_pool], 3)
          end_points['mixed_17x17x768a'] = net
        # mixed4: 17 x 17 x 768.
        with tf.variable_scope('mixed_17x17x768b'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 192, [1, 1])
          with tf.variable_scope('branch7x7'):
            branch7x7 = ops.conv2d(net, 128, [1, 1])
            branch7x7 = ops.conv2d(branch7x7, 128, [1, 7])
            branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
          with tf.variable_scope('branch7x7dbl'):
            branch7x7dbl = ops.conv2d(net, 128, [1, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [1, 7])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 128, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
          net = tf.concat([branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
          end_points['mixed_17x17x768b'] = net
        # mixed_5: 17 x 17 x 768.
        with tf.variable_scope('mixed_17x17x768c'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 192, [1, 1])
          with tf.variable_scope('branch7x7'):
            branch7x7 = ops.conv2d(net, 160, [1, 1])
            branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
            branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
          with tf.variable_scope('branch7x7dbl'):
            branch7x7dbl = ops.conv2d(net, 160, [1, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
          net = tf.concat([branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
          end_points['mixed_17x17x768c'] = net
        # mixed_6: 17 x 17 x 768.
        with tf.variable_scope('mixed_17x17x768d'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 192, [1, 1])
          with tf.variable_scope('branch7x7'):
            branch7x7 = ops.conv2d(net, 160, [1, 1])
            branch7x7 = ops.conv2d(branch7x7, 160, [1, 7])
            branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
          with tf.variable_scope('branch7x7dbl'):
            branch7x7dbl = ops.conv2d(net, 160, [1, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [1, 7])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 160, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
          net = tf.concat([branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
          end_points['mixed_17x17x768d'] = net
        # mixed_7: 17 x 17 x 768.
        with tf.variable_scope('mixed_17x17x768e'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 192, [1, 1])
          with tf.variable_scope('branch7x7'):
            branch7x7 = ops.conv2d(net, 192, [1, 1])
            branch7x7 = ops.conv2d(branch7x7, 192, [1, 7])
            branch7x7 = ops.conv2d(branch7x7, 192, [7, 1])
          with tf.variable_scope('branch7x7dbl'):
            branch7x7dbl = ops.conv2d(net, 192, [1, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [7, 1])
            branch7x7dbl = ops.conv2d(branch7x7dbl, 192, [1, 7])
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
          net = tf.concat([branch1x1, branch7x7, branch7x7dbl, branch_pool], 3)
          end_points['mixed_17x17x768e'] = net
        # Auxiliary Head logits
        aux_logits = tf.identity(end_points['mixed_17x17x768e'])
        with tf.variable_scope('aux_logits'):
          aux_logits = ops.avg_pool(aux_logits, [5, 5], stride=3,
                                    padding='VALID')
          aux_logits = ops.conv2d(aux_logits, 128, [1, 1], scope='proj')
          # Shape of feature map before the final layer.
          shape = aux_logits.get_shape()
          aux_logits = ops.conv2d(aux_logits, 768, shape[1:3], stddev=0.01,
                                  padding='VALID')
          aux_logits = ops.flatten(aux_logits)
          aux_logits = ops.fc(aux_logits, num_classes, activation=None,
                              stddev=0.001, restore=restore_logits)
          end_points['aux_logits'] = aux_logits
        # mixed_8: 8 x 8 x 1280.
        # Note that the scope below is not changed to not void previous
        # checkpoints.
        # (TODO) Fix the scope when appropriate.
        with tf.variable_scope('mixed_17x17x1280a'):
          with tf.variable_scope('branch3x3'):
            branch3x3 = ops.conv2d(net, 192, [1, 1])
            branch3x3 = ops.conv2d(branch3x3, 320, [3, 3], stride=2,
                                   padding='VALID')
          with tf.variable_scope('branch7x7x3'):
            branch7x7x3 = ops.conv2d(net, 192, [1, 1])
            branch7x7x3 = ops.conv2d(branch7x7x3, 192, [1, 7])
            branch7x7x3 = ops.conv2d(branch7x7x3, 192, [7, 1])
            branch7x7x3 = ops.conv2d(branch7x7x3, 192, [3, 3],
                                     stride=2, padding='VALID')
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.max_pool(net, [3, 3], stride=2, padding='VALID')
          net = tf.concat([branch3x3, branch7x7x3, branch_pool], 3)
          end_points['mixed_17x17x1280a'] = net
        # mixed_9: 8 x 8 x 2048.
        with tf.variable_scope('mixed_8x8x2048a'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 320, [1, 1])
          with tf.variable_scope('branch3x3'):
            branch3x3 = ops.conv2d(net, 384, [1, 1])
            branch3x3 = tf.concat([ops.conv2d(branch3x3, 384, [1, 3]),
                                   ops.conv2d(branch3x3, 384, [3, 1])], 3)
          with tf.variable_scope('branch3x3dbl'):
            branch3x3dbl = ops.conv2d(net, 448, [1, 1])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
            branch3x3dbl = tf.concat([ops.conv2d(branch3x3dbl, 384, [1, 3]),
                                      ops.conv2d(branch3x3dbl, 384, [3, 1])], 3)
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
          net = tf.concat([branch1x1, branch3x3, branch3x3dbl, branch_pool], 3)
          end_points['mixed_8x8x2048a'] = net
        # mixed_10: 8 x 8 x 2048.
        with tf.variable_scope('mixed_8x8x2048b'):
          with tf.variable_scope('branch1x1'):
            branch1x1 = ops.conv2d(net, 320, [1, 1])
          with tf.variable_scope('branch3x3'):
            branch3x3 = ops.conv2d(net, 384, [1, 1])
            branch3x3 = tf.concat([ops.conv2d(branch3x3, 384, [1, 3]),
                                   ops.conv2d(branch3x3, 384, [3, 1])], 3)
          with tf.variable_scope('branch3x3dbl'):
            branch3x3dbl = ops.conv2d(net, 448, [1, 1])
            branch3x3dbl = ops.conv2d(branch3x3dbl, 384, [3, 3])
            branch3x3dbl = tf.concat([ops.conv2d(branch3x3dbl, 384, [1, 3]),
                                      ops.conv2d(branch3x3dbl, 384, [3, 1])], 3)
          with tf.variable_scope('branch_pool'):
            branch_pool = ops.avg_pool(net, [3, 3])
            branch_pool = ops.conv2d(branch_pool, 192, [1, 1])
          net = tf.concat([branch1x1, branch3x3, branch3x3dbl, branch_pool], 3)
          end_points['mixed_8x8x2048b'] = net
        # Final pooling and prediction
        with tf.variable_scope('logits'):
          shape = net.get_shape()
          net = ops.avg_pool(net, shape[1:3], padding='VALID', scope='pool')
          # 1 x 1 x 2048
          net = ops.dropout(net, dropout_keep_prob, scope='dropout')
          net = ops.flatten(net, scope='flatten')
          # 2048
          logits = ops.fc(net, num_classes, activation=None, scope='logits',
                          restore=restore_logits)
          # 1000
          end_points['logits'] = logits
          end_points['predictions'] = tf.nn.softmax(logits, name='predictions')
      return logits, end_points
예제 #12
0
def vgg_16(inputs,
                 dropout_keep_prob=0.8,
                 num_classes=10,
                 is_training=True,
                 restore_logits=True,
                 scope=''):
  """Latest Inception from http://arxiv.org/abs/1512.00567.

    "Rethinking the Inception Architecture for Computer Vision"

    Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
    Zbigniew Wojna

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    dropout_keep_prob: dropout keep_prob.
    num_classes: number of predicted classes.
    is_training: whether is training or not.
    restore_logits: whether or not the logits layers should be restored.
      Useful for fine-tuning a model with different num_classes.
    scope: Optional scope for op_scope.

  Returns:
    a list containing 'logits', 'aux_logits' Tensors.
  """
  # end_points will collect relevant activations for external use, for example
  # summaries or losses.
  dropout_keep_prob = 0.4 if training else 1.0
  
  end_points = {}
  with tf.op_scope([inputs], scope, 'vgg_16'):
    with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
                          is_training=is_training):
      with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                            stride=1, padding='SAME'):
        # assume input_op shape is 224x224x3
        # block 1 -- outputs 112x112x64
        end_points['conv1_1'] = ops.conv2d(inputs, 64, [3, 3], stride=1,
                                         scope='conv1_1')
        end_points['conv1_2'] = ops.conv2d(end_points['conv1_1'], 64, [3, 3],
                                         scope='conv1_2')
        end_points['pool1'] = ops.max_pool(end_points['conv1_2'], [2, 2],
                                          stride=2, scope='pool1')

        # block 2 -- outputs 56x56x128
        end_points['conv2_1'] = ops.conv2d(end_points['pool1'], 128, [3, 3],
                                         scope='conv2_1')
        end_points['conv2_2'] = ops.conv2d(end_points['conv2_1'], 128, [3, 3],
                                         scope='conv2_2')
        end_points['pool2'] = ops.max_pool(end_points['conv2_2'], [2, 2],
                                           stride=2, scope='pool2')
        # block 3 -- outputs 28x28x256
        end_points['conv3_1'] = ops.conv2d(end_points['pool2'], 256, [3, 3],
                                         scope='conv3_1')
        end_points['conv3_2'] = ops.conv2d(end_points['conv3_1'], 256, [3, 3],
                                         scope='conv3_2')
        end_points['pool3'] = ops.max_pool(end_points['conv3_2'], [2, 2],
                                           stride=2, scope='pool3')

        # block 4 -- outputs 14x14x512
        end_points['conv4_1'] = ops.conv2d(end_points['pool3'], 512, [3, 3],
                                         scope='conv4_1')
        end_points['conv4_2'] = ops.conv2d(end_points['conv4_1'], 512, [3, 3],
                                         scope='conv4_2')
        end_points['pool4'] = ops.max_pool(end_points['conv4_2'], [2, 2],
                                           stride=2, scope='pool4')

        # block 5 -- outputs 7x7x512
        end_points['conv5_1'] = ops.conv2d(end_points['pool4'], 512, [3, 3],
                                         scope='conv5_1')
        end_points['conv5_2'] = ops.conv2d(end_points['conv5_1'], 512, [3, 3],
                                         scope='conv5_2')
        end_points['pool5'] = ops.max_pool(end_points['conv5_2'], [2, 2],
                                           stride=2, scope='pool5')

        net = end_points['pool5']

        # Final pooling and prediction
        with tf.variable_scope('logits'):
          # flatten
          net = ops.flatten(net, scope='flatten')

          # fully connected
          end_points['fc6'] = ops.fc(net, 1000, activation=None, scope='fc6',
                          restore=restore_logits)
          end_points['fc6_drop'] = ops.dropout(end_points['fc6'], dropout_keep_prob, scope='fc6_drop')

          end_points['fc7'] = ops.fc(end_points['fc6_drop'], 50, activation=None, scope='fc7',
                          restore=restore_logits)
          end_points['fc7_drop'] = ops.dropout(end_points['fc7'], dropout_keep_prob, scope='fc7_drop')

          end_points['fc8'] = ops.fc(end_points['fc7_drop'], num_classes, activation=None, scope='fc8',
                          restore=restore_logits)
          end_points['fc8_drop'] = ops.dropout(end_points['fc8'], dropout_keep_prob, scope='fc8_drop')

          logits = end_points['fc8_drop']
          end_points['logits'] = logits
          end_points['predictions'] = tf.nn.softmax(logits, name='predictions')
      return logits, end_points
예제 #13
0
def alexnet(inputs,
                 dropout_keep_prob=0.8,
                 num_classes=1000,
                 is_training=True,
                 restore_logits=True,
                 scope=''):
  """Latest Inception from http://arxiv.org/abs/1512.00567.

    "Rethinking the Inception Architecture for Computer Vision"

    Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens,
    Zbigniew Wojna

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    dropout_keep_prob: dropout keep_prob.
    num_classes: number of predicted classes.
    is_training: whether is training or not.
    restore_logits: whether or not the logits layers should be restored.
      Useful for fine-tuning a model with different num_classes.
    scope: Optional scope for op_scope.

  Returns:
    a list containing 'logits', 'aux_logits' Tensors.
  """
  # end_points will collect relevant activations for external use, for example
  # summaries or losses.
  end_points = {}
  with tf.op_scope([inputs], scope, 'alexnet'):
    with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
                          is_training=is_training):
      # conv and pool will do padding
      with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                            padding='SAME'):
        # define the initial distribution of filter weight
        with scopes.arg_scope([ops.conv2d], stddev=0.01):
          end_points['conv1'] = ops.conv2d(inputs, 96, [11, 11], stride=4,
                                           scope='conv1')
          end_points['pool1'] = ops.max_pool(end_points['conv1'], [3, 3],
                                             stride=2, scope='pool1')
          end_points['conv2'] = ops.conv2d(end_points['pool1'], 256, [5, 5],
                                           bias=1.0, scope='conv2')
          end_points['pool2'] = ops.max_pool(end_points['conv2'], [3, 3],
                                             stride=2, scope='pool2')
          end_points['conv3'] = ops.conv2d(end_points['pool2'], 384, [3, 3],
                                           scope='conv3')
          end_points['conv4'] = ops.conv2d(end_points['conv3'], 384, [3, 3],
                                           bias=1.0, scope='conv4')
          end_points['conv5'] = ops.conv2d(end_points['conv4'], 256, [3, 3],
                                           bias=1.0, scope='conv5')
          end_points['pool5'] = ops.max_pool(end_points['conv5'], [3, 3],
                                             stride=2, scope='pool5')

      # reshape the 4d tensor into 2d
      end_points['flatten'] = ops.flatten(end_points['pool5'], scope='flatten')

      # define the initial distribution of fc weight
      with scopes.arg_scope([ops.fc], stddev=0.005, bias=1.0):
        # define the dropout ratio
        with scopes.arg_scope([ops.dropout], keep_prob=dropout_keep_prob):
          end_points['fc6'] = ops.fc(end_points['flatten'], 4096, scope='fc6')
          end_points['drop6'] = ops.dropout(end_points['fc6'], scope='drop6')
          end_points['fc7'] = ops.fc(end_points['drop6'], 4096, scope='fc7')
          end_points['drop7'] = ops.dropout(end_points['fc7'], scope='drop7')
          end_points['fc8'] = ops.fc(end_points['drop7'], num_classes,
                                     activation=None,
                                     scope='fc8', restore=restore_logits)
      return end_points['fc8'], end_points
예제 #14
0
def alexnet(inputs,
                 dropout_keep_prob=0.5,
                 num_classes=1000,
                 is_training=True,
                 restore_logits=True,
                 seed=1,
                 weight_decay=0.0005,
                 scope=''):
  """AlexNet from https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.

  Args:
    inputs: a tensor of size [batch_size, height, width, channels].
    dropout_keep_prob: dropout keep_prob.
    num_classes: number of predicted classes.
    is_training: whether is training or not.
    restore_logits: whether or not the logits layers should be restored.
      Useful for fine-tuning a model with different num_classes.
    scope: Optional scope for name_scope.

  Returns:
    a list containing 'logits', 'aux_logits' Tensors.
  """
  # end_points will collect relevant activations for external use, for example
  # summaries or losses.
  #print ("INFO: batch norm in alexnet is disabled")
  end_points = {}
  with tf.name_scope(scope, 'alexnet', [inputs]):
    with scopes.arg_scope([ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
                          is_training=is_training):
      with scopes.arg_scope([ops.conv2d, ops.fc],
                            weight_decay=weight_decay, stddev=0.01, bias=0.1,
                            #batch_norm_params=None,
                            weights_initializer=tf.truncated_normal_initializer):
        with scopes.arg_scope([ops.conv2d],
                              stride=1, padding='SAME'):
          with scopes.arg_scope([ops.max_pool],
                                stride=2, padding='VALID'):
            # 224 x 224 x 3
            end_points['conv1_1'] = ops.conv2d(inputs, 48, [11, 11], stride=4, bias=0.0, seed = seed +1, scope='conv1_1')
            end_points['conv1_2'] = ops.conv2d(inputs, 48, [11, 11], stride=4, bias=0.0, seed = seed +2, scope='conv1_2')
            end_points['lrn1_1'] = ops.lrn(end_points['conv1_1'], scope='lrn1_1')
            end_points['lrn1_2'] = ops.lrn(end_points['conv1_2'], scope='lrn1_2')
            end_points['pool1_1'] = ops.max_pool(end_points['lrn1_1'], [3, 3], scope='pool1_1')
            end_points['pool1_2'] = ops.max_pool(end_points['lrn1_2'], [3, 3], scope='pool1_2')

            # 27 x 27 x 48 x 2
            end_points['conv2_1'] = ops.conv2d(end_points['pool1_1'], 128, [5, 5], seed = seed +3, scope='conv2_1')
            end_points['conv2_2'] = ops.conv2d(end_points['pool1_2'], 128, [5, 5], seed = seed +4, scope='conv2_2')
            end_points['lrn2_1'] = ops.lrn(end_points['conv2_1'], scope='lrn2_1')
            end_points['lrn2_2'] = ops.lrn(end_points['conv2_2'], scope='lrn2_2')
            end_points['pool2_1'] = ops.max_pool(end_points['lrn2_1'], [3, 3], scope='pool2_1')
            end_points['pool2_2'] = ops.max_pool(end_points['lrn2_2'], [3, 3], scope='pool2_2')
            end_points['pool2'] = tf.concat([end_points['pool2_1'],end_points['pool2_2']],3)

            # 13 x 13 x 256
            end_points['conv3_1'] = ops.conv2d(end_points['pool2'], 192, [3, 3], bias=0.0, seed = seed +5, scope='conv3_1')
            end_points['conv3_2'] = ops.conv2d(end_points['pool2'], 192, [3, 3], bias=0.0, seed = seed +6, scope='conv3_2')

            # 13 x 13 x 192 x 2
            end_points['conv4_1'] = ops.conv2d(end_points['conv3_1'], 192, [3, 3], seed = seed +7, scope='conv4_1')
            end_points['conv4_2'] = ops.conv2d(end_points['conv3_2'], 192, [3, 3], seed = seed +8, scope='conv4_2')

            # 13 x 13 x 192 x 2
            end_points['conv5_1'] = ops.conv2d(end_points['conv4_1'], 128, [3, 3], seed = seed +9, scope='conv5_1')
            end_points['conv5_2'] = ops.conv2d(end_points['conv4_2'], 128, [3, 3], seed = seed +10, scope='conv5_2')
            end_points['pool5_1'] = ops.max_pool(end_points['conv5_1'], [3, 3], scope='pool5_1')
            end_points['pool5_2'] = ops.max_pool(end_points['conv5_2'], [3, 3], scope='pool5_2')
            end_points['pool5'] = tf.concat([end_points['pool5_1'], end_points['pool5_2']], 3)

            end_points['pool5'] = ops.flatten(end_points['pool5'], scope='flatten')
            end_points['fc6'] = ops.fc(end_points['pool5'], 4096, stddev=0.005, seed = seed +11, scope='fc6')
            end_points['dropout6'] = ops.dropout(end_points['fc6'], dropout_keep_prob, scope='dropout6')
            end_points['fc7'] = ops.fc(end_points['dropout6'], 4096, stddev=0.005, seed = seed +12, scope='fc7')
            net = ops.dropout(end_points['fc7'], dropout_keep_prob, scope='dropout7')

            # Final pooling and prediction
            with tf.variable_scope('logits'):
              # 4096
              logits = ops.fc(net, num_classes, activation=None, bias=0.0, seed = seed +13, scope='logits',
                              restore=restore_logits)
              # 1000
              end_points['logits'] = logits
              end_points['predictions'] = tf.nn.softmax(logits, name='predictions')
  # There is no aux_logits for AlexNet
  end_points['aux_logits'] = tf.constant(0)
  return logits, end_points
예제 #15
0
def inception_v1(inputs,
                 dropout_keep_prob=0.8,
                 num_classes=1000,
                 is_training=True,
                 restore_logits=True,
                 scope=''):
    """inception v1
  Returns:
    a list like ('logits', ) of Tensors.
  """
    # end_points will collect relevant activations for external use, for example
    # summaries or losses.
    end_points = {}
    with tf.op_scope([inputs], scope, 'InceptionV1'):
        with scopes.arg_scope(
            [ops.conv2d, ops.fc, ops.batch_norm, ops.dropout],
                is_training=is_training):
            # replaces weights_initializer with trunc_norm(0.01) since w_i is not specified
            with scopes.arg_scope([ops.conv2d, ops.fc], stddev=0.01):
                with scopes.arg_scope([ops.conv2d, ops.max_pool, ops.avg_pool],
                                      stride=1,
                                      padding='SAME'):
                    end_point = 'Conv2d_1a_7x7'
                    net = ops.conv2d(inputs,
                                     64, [7, 7],
                                     stride=2,
                                     scope=end_point)
                    end_points[end_point] = net
                    end_point = 'MaxPool_2a_3x3'
                    net = ops.max_pool(net, [3, 3], stride=2, scope=end_point)
                    end_points[end_point] = net
                    end_point = 'Conv2d_2b_1x1'
                    net = ops.conv2d(net, 64, [1, 1], scope=end_point)
                    end_points[end_point] = net
                    end_point = 'Conv2d_2c_3x3'
                    net = ops.conv2d(net, 192, [3, 3], scope=end_point)
                    end_points[end_point] = net
                    end_point = 'MaxPool_3a_3x3'
                    net = ops.max_pool(net, [3, 3], stride=2, scope=end_point)
                    end_points[end_point] = net

                    end_point = 'Mixed_3b'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  64, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  96, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  128, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  16, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  32, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            print('net shape before 3x3 maxpool is:' +
                                  str(net))
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            print('net shape after maxpool is:' +
                                  str(branch_3))
                            branch_3 = ops.conv2d(branch_3,
                                                  32, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'Mixed_3c'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  128, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  128, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  192, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  32, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  96, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  64, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'MaxPool_4a_3x3'
                    net = ops.max_pool(net, [3, 3], stride=2, scope=end_point)
                    end_points[end_point] = net

                    end_point = 'Mixed_4b'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  192, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  96, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  208, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  16, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  48, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  64, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'Mixed_4c'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  160, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  112, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  224, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  24, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  64, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  64, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'Mixed_4d'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  128, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  128, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  256, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  24, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  64, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  64, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'Mixed_4e'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  112, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  144, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  288, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  32, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  64, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  64, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'Mixed_4f'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  256, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  160, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  320, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  32, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  128, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  128, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'MaxPool_5a_2x2'
                    net = ops.max_pool(net, [2, 2], stride=2, scope=end_point)
                    end_points[end_point] = net

                    end_point = 'Mixed_5b'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  256, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  160, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  320, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  32, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  128, [3, 3],
                                                  scope='Conv2d_0a_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  128, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    end_point = 'Mixed_5c'
                    with tf.variable_scope(end_point):
                        with tf.variable_scope('Branch_0'):
                            branch_0 = ops.conv2d(net,
                                                  384, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                        with tf.variable_scope('Branch_1'):
                            branch_1 = ops.conv2d(net,
                                                  192, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_1 = ops.conv2d(branch_1,
                                                  384, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_2'):
                            branch_2 = ops.conv2d(net,
                                                  48, [1, 1],
                                                  scope='Conv2d_0a_1x1')
                            branch_2 = ops.conv2d(branch_2,
                                                  128, [3, 3],
                                                  scope='Conv2d_0b_3x3')
                        with tf.variable_scope('Branch_3'):
                            branch_3 = ops.max_pool(net, [3, 3],
                                                    scope='MaxPool_0a_3x3')
                            branch_3 = ops.conv2d(branch_3,
                                                  128, [1, 1],
                                                  scope='Conv2d_0b_1x1')
                        net = tf.concat(
                            3, [branch_0, branch_1, branch_2, branch_3])
                    end_points[end_point] = net

                    # Final pooling and prediction
                    with tf.variable_scope('Logits'):
                        # TODO fix this being in argscope and instead manually supply the correct weights_initializer fn
                        # which is probably xavier_initializer() or something
                        net = ops.avg_pool(net, [7, 7],
                                           stride=1,
                                           scope='MaxPool_0a_7x7',
                                           padding='VALID')
                        net = ops.dropout(net,
                                          dropout_keep_prob,
                                          scope='Dropout_0b')
                        logits = ops.conv2d(net,
                                            num_classes, [1, 1],
                                            activation=None,
                                            batch_norm_params=None,
                                            scope='Conv2d_0c_1x1')
                        logits = tf.squeeze(logits, [1, 2],
                                            name='SpatialSqueeze')
                        end_points['Logits'] = logits
                        end_points['Predictions'] = tf.nn.softmax(
                            logits, name='Predictions')
                [print(v.name) for v in tf.all_variables()]
                return logits, end_points