Python tensorflow.contrib.slim.max_pool2d() Examples

def _image_to_head(self, is_training, reuse=None):
        with tf.variable_scope(self._scope, self._scope, reuse=reuse):
            net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3],
                              trainable=True, scope='conv1')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1')
            net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3],
                              trainable=True, scope='conv2')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2')
            net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3],
                              trainable=True, scope='conv3')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3')
            net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3],
                              trainable=True, scope='conv4')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4')
            net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3],
                              trainable=True, scope='conv5')

        self._act_summaries.append(net)
        self._layers['head'] = net

        return net 

def block_inception_a(inputs, scope=None, reuse=None):
  """Builds Inception-A block for Inception v4 network."""
  # By default use stride=1 and SAME padding
  with slim.arg_scope(
      [slim.conv2d, slim.avg_pool2d, slim.max_pool2d], stride=1,
      padding='SAME'):
    with variable_scope.variable_scope(
        scope, 'BlockInceptionA', [inputs], reuse=reuse):
      with variable_scope.variable_scope('Branch_0'):
        branch_0 = slim.conv2d(inputs, 96, [1, 1], scope='Conv2d_0a_1x1')
      with variable_scope.variable_scope('Branch_1'):
        branch_1 = slim.conv2d(inputs, 64, [1, 1], scope='Conv2d_0a_1x1')
        branch_1 = slim.conv2d(branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
      with variable_scope.variable_scope('Branch_2'):
        branch_2 = slim.conv2d(inputs, 64, [1, 1], scope='Conv2d_0a_1x1')
        branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
        branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
      with variable_scope.variable_scope('Branch_3'):
        branch_3 = slim.avg_pool2d(inputs, [3, 3], scope='AvgPool_0a_3x3')
        branch_3 = slim.conv2d(branch_3, 96, [1, 1], scope='Conv2d_0b_1x1')
      return array_ops.concat(
          axis=3, values=[branch_0, branch_1, branch_2, branch_3]) 

def E(self, images, is_training = False, reuse=False):
	
	if images.get_shape()[3] == 3:
	    images = tf.image.rgb_to_grayscale(images)
	
	with tf.variable_scope('encoder',reuse=reuse):
	    with slim.arg_scope([slim.fully_connected], activation_fn=tf.nn.relu):
		with slim.arg_scope([slim.conv2d], activation_fn=tf.nn.relu, padding='VALID'):
		    net = slim.conv2d(images, 64, 5, scope='conv1')
		    net = slim.max_pool2d(net, 2, stride=2, scope='pool1')
		    net = slim.conv2d(net, 128, 5, scope='conv2')
		    net = slim.max_pool2d(net, 2, stride=2, scope='pool2')
		    net = tf.contrib.layers.flatten(net)
		    net = slim.fully_connected(net, 1024, activation_fn=tf.nn.relu, scope='fc3')
		    net = slim.dropout(net, 0.5, is_training=is_training)
		    net = slim.fully_connected(net, self.hidden_repr_size, activation_fn=tf.tanh,scope='fc4')
		    # dropout here or not?
		    #~ net = slim.dropout(net, 0.5, is_training=is_training)
		    return net 

def AddMaxPool(self, prev_layer, index):
    """Add a maxpool layer.

    Args:
      prev_layer: Input tensor.
      index:      Position in model_str to start parsing

    Returns:
      Output tensor, end index in model_str.
    """
    pattern = re.compile(R'(Mp)({\w+})?(\d+),(\d+)(?:,(\d+),(\d+))?')
    m = pattern.match(self.model_str, index)
    if m is None:
      return None, None
    name = self._GetLayerName(m.group(0), index, m.group(2))
    height = int(m.group(3))
    width = int(m.group(4))
    y_stride = height if m.group(5) is None else m.group(5)
    x_stride = width if m.group(6) is None else m.group(6)
    self.reduction_factors[1] *= y_stride
    self.reduction_factors[2] *= x_stride
    return slim.max_pool2d(
        prev_layer, [height, width], [y_stride, x_stride],
        padding='SAME',
        scope=name), m.end() 

def stem_stack_3x3(net, input_channel=32, scope="C1"):
    with tf.variable_scope(scope):
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.conv2d(net, num_outputs=input_channel, kernel_size=[3, 3], stride=2,
                          padding="VALID", biases_initializer=None, data_format=DATA_FORMAT,
                          scope='conv0')
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.conv2d(net, num_outputs=input_channel, kernel_size=[3, 3], stride=1,
                          padding="VALID", biases_initializer=None, data_format=DATA_FORMAT,
                          scope='conv1')
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.conv2d(net, num_outputs=input_channel*2, kernel_size=[3, 3], stride=1,
                          padding="VALID", biases_initializer=None, data_format=DATA_FORMAT,
                          scope='conv2')
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.max_pool2d(net, kernel_size=[3, 3], stride=2, padding="VALID", data_format=DATA_FORMAT)
        return net 

def AddMaxPool(self, prev_layer, index):
    """Add a maxpool layer.

    Args:
      prev_layer: Input tensor.
      index:      Position in model_str to start parsing

    Returns:
      Output tensor, end index in model_str.
    """
    pattern = re.compile(R'(Mp)({\w+})?(\d+),(\d+)(?:,(\d+),(\d+))?')
    m = pattern.match(self.model_str, index)
    if m is None:
      return None, None
    name = self._GetLayerName(m.group(0), index, m.group(2))
    height = int(m.group(3))
    width = int(m.group(4))
    y_stride = height if m.group(5) is None else m.group(5)
    x_stride = width if m.group(6) is None else m.group(6)
    self.reduction_factors[1] *= y_stride
    self.reduction_factors[2] *= x_stride
    return slim.max_pool2d(
        prev_layer, [height, width], [y_stride, x_stride],
        padding='SAME',
        scope=name), m.end() 

def max_pool_views(self, nets_list):
    """Max pool across all nets in spatial dimensions.

    Args:
      nets_list: A list of 4D tensors with identical size.

    Returns:
      A tensor with the same size as any input tensors.
    """
    batch_size, height, width, num_features = [
      d.value for d in nets_list[0].get_shape().dims
    ]
    xy_flat_shape = (batch_size, 1, height * width, num_features)
    nets_for_merge = []
    with tf.variable_scope('max_pool_views', values=nets_list):
      for net in nets_list:
        nets_for_merge.append(tf.reshape(net, xy_flat_shape))
      merged_net = tf.concat(nets_for_merge, 1)
      net = slim.max_pool2d(
        merged_net, kernel_size=[len(nets_list), 1], stride=1)
      net = tf.reshape(net, (batch_size, height, width, num_features))
    return net 

def reduction_b(net):
    with tf.variable_scope('Branch_0'):
        tower_conv = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
        tower_conv_1 = slim.conv2d(tower_conv, 384, 3, stride=2,
                                   padding='VALID', scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_1'):
        tower_conv1 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
        tower_conv1_1 = slim.conv2d(tower_conv1, 256, 3, stride=2,
                                    padding='VALID', scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_2'):
        tower_conv2 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
        tower_conv2_1 = slim.conv2d(tower_conv2, 256, 3,
                                    scope='Conv2d_0b_3x3')
        tower_conv2_2 = slim.conv2d(tower_conv2_1, 256, 3, stride=2,
                                    padding='VALID', scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_3'):
        tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID',
                                     scope='MaxPool_1a_3x3')
    net = tf.concat([tower_conv_1, tower_conv1_1,
                        tower_conv2_2, tower_pool], 3)
    return net 

def reduction_a(net, k, l, m, n):
    with tf.variable_scope('Branch_0'):
        tower_conv = slim.conv2d(net, n, 3, stride=2, padding='VALID',
                                 scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_1'):
        tower_conv1_0 = slim.conv2d(net, k, 1, scope='Conv2d_0a_1x1')
        tower_conv1_1 = slim.conv2d(tower_conv1_0, l, 3,
                                    scope='Conv2d_0b_3x3')
        tower_conv1_2 = slim.conv2d(tower_conv1_1, m, 3,
                                    stride=2, padding='VALID',
                                    scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_2'):
        tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID',
                                     scope='MaxPool_1a_3x3')
    net = tf.concat([tower_conv, tower_conv1_2, tower_pool], 3)
    return net 

def max_pool_views(self, nets_list):
    """Max pool across all nets in spatial dimensions.

    Args:
      nets_list: A list of 4D tensors with identical size.

    Returns:
      A tensor with the same size as any input tensors.
    """
    batch_size, height, width, num_features = [
        d.value for d in nets_list[0].get_shape().dims
    ]
    xy_flat_shape = (batch_size, 1, height * width, num_features)
    nets_for_merge = []
    with tf.variable_scope('max_pool_views', values=nets_list):
      for net in nets_list:
        nets_for_merge.append(tf.reshape(net, xy_flat_shape))
      merged_net = tf.concat(nets_for_merge, 1)
      net = slim.max_pool2d(
          merged_net, kernel_size=[len(nets_list), 1], stride=1)
      net = tf.reshape(net, (batch_size, height, width, num_features))
    return net 

def stem_stack_3x3(net, input_channel=32, scope="C1"):
    with tf.variable_scope(scope):
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.conv2d(net, num_outputs=input_channel, kernel_size=[3, 3], stride=2,
                          padding="VALID", biases_initializer=None, data_format=DATA_FORMAT,
                          scope='conv0')
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.conv2d(net, num_outputs=input_channel, kernel_size=[3, 3], stride=1,
                          padding="VALID", biases_initializer=None, data_format=DATA_FORMAT,
                          scope='conv1')
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.conv2d(net, num_outputs=input_channel*2, kernel_size=[3, 3], stride=1,
                          padding="VALID", biases_initializer=None, data_format=DATA_FORMAT,
                          scope='conv2')
        net = tf.pad(net, paddings=[[0, 0], [1, 1], [1, 1], [0, 0]])
        net = slim.max_pool2d(net, kernel_size=[3, 3], stride=2, padding="VALID", data_format=DATA_FORMAT)
        return net 

def _crop_pool_layer(self, bottom, rois, name):
        with tf.variable_scope(name) as scope:
            batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
            # Get the normalized coordinates of bounding boxes
            bottom_shape = tf.shape(bottom)
            height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
            width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
            x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
            y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
            x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
            y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
            # Won't be back-propagated to rois anyway, but to save time
            bboxes = tf.stop_gradient(tf.concat([y1, x1, y2, x2], axis=1))
            pre_pool_size = cfg.POOLING_SIZE * 2
            crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids),
                                             [pre_pool_size, pre_pool_size],
                                             name="crops")

        # slim.max_pool2d has stride 2 in default
        return slim.max_pool2d(crops, [2, 2], padding='SAME') 

def _crop_pool_layer(self, bottom, rois, name):
    with tf.variable_scope(name) as scope:
      batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
      # Get the normalized coordinates of bboxes
      bottom_shape = tf.shape(bottom)
      height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
      width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
      x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
      y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
      x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
      y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
      # Won't be backpropagated to rois anyway, but to save time
      bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
      if cfg.RESNET.MAX_POOL:
        pre_pool_size = cfg.POOLING_SIZE * 2
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],
                                         name="crops")
        crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
      else:
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [cfg.POOLING_SIZE, cfg.POOLING_SIZE],
                                         name="crops")
    return crops

  # Do the first few layers manually, because 'SAME' padding can behave inconsistently
  # for images of different sizes: sometimes 0, sometimes 1 

def _extra_conv_arg_scope_with_bn(weight_decay=0.00001,
                     activation_fn=None,
                     batch_norm_decay=0.997,
                     batch_norm_epsilon=1e-5,
                     batch_norm_scale=True):

  batch_norm_params = {
      'decay': batch_norm_decay,
      'epsilon': batch_norm_epsilon,
      'scale': batch_norm_scale,
      'updates_collections': tf.GraphKeys.UPDATE_OPS,
  }

  with slim.arg_scope(
      [slim.conv2d],
      weights_regularizer=slim.l2_regularizer(weight_decay),
      weights_initializer=slim.variance_scaling_initializer(),
      activation_fn=tf.nn.relu,
      normalizer_fn=slim.batch_norm,
      normalizer_params=batch_norm_params):
    with slim.arg_scope([slim.batch_norm], **batch_norm_params):
      with slim.arg_scope([slim.max_pool2d], padding='SAME') as arg_sc:
        return arg_sc 

def _crop_pool_layer(self, bottom, rois, name):
    with tf.variable_scope(name) as scope:
      batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
      # Get the normalized coordinates of bboxes
      bottom_shape = tf.shape(bottom)
      height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
      width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
      x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
      y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
      x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
      y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
      # Won't be backpropagated to rois anyway, but to save time
      bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
      pre_pool_size = cfg.POOLING_SIZE * 2
      crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size], name="crops")

    return slim.max_pool2d(crops, [2, 2], padding='SAME') 

def _image_to_head(self, is_training, reuse=None):
        with tf.variable_scope(self._vgg_scope, self._vgg_scope, reuse=reuse):
            net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3],
                              trainable=False, scope='conv1')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1')
            net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3],
                              trainable=False, scope='conv2')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2')
            net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3],
                              trainable=is_training, scope='conv3')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3')
            net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3],
                              trainable=is_training, scope='conv4')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4')
            net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3],
                              trainable=is_training, scope='conv5')

        self._act_summaries.append(net)
        self._layers['head'] = net

        return net 

def _crop_pool_layer(self, bottom, rois, name):
    with tf.variable_scope(name) as scope:
      batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
      # Get the normalized coordinates of bboxes
      bottom_shape = tf.shape(bottom)
      height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
      width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
      x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
      y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
      x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
      y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
      # Won't be backpropagated to rois anyway, but to save time
      bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
      if cfg.RESNET.MAX_POOL:
        pre_pool_size = cfg.POOLING_SIZE * 2
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],
                                         name="crops")
        crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
      else:
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [cfg.POOLING_SIZE, cfg.POOLING_SIZE],
                                         name="crops")
    return crops

  # Do the first few layers manually, because 'SAME' padding can behave inconsistently
  # for images of different sizes: sometimes 0, sometimes 1 

def reduction_a(net, k, l, m, n):
    with tf.variable_scope('Branch_0'):
        tower_conv = slim.conv2d(net, n, 3, stride=2, padding='VALID',
                                 scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_1'):
        tower_conv1_0 = slim.conv2d(net, k, 1, scope='Conv2d_0a_1x1')
        tower_conv1_1 = slim.conv2d(tower_conv1_0, l, 3,
                                    scope='Conv2d_0b_3x3')
        tower_conv1_2 = slim.conv2d(tower_conv1_1, m, 3,
                                    stride=2, padding='VALID',
                                    scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_2'):
        tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID',
                                     scope='MaxPool_1a_3x3')
    net = tf.concat([tower_conv, tower_conv1_2, tower_pool], 3)
    return net 

def reduction_b(net):
    with tf.variable_scope('Branch_0'):
        tower_conv = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
        tower_conv_1 = slim.conv2d(tower_conv, 384, 3, stride=2,
                                   padding='VALID', scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_1'):
        tower_conv1 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
        tower_conv1_1 = slim.conv2d(tower_conv1, 256, 3, stride=2,
                                    padding='VALID', scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_2'):
        tower_conv2 = slim.conv2d(net, 256, 1, scope='Conv2d_0a_1x1')
        tower_conv2_1 = slim.conv2d(tower_conv2, 256, 3,
                                    scope='Conv2d_0b_3x3')
        tower_conv2_2 = slim.conv2d(tower_conv2_1, 256, 3, stride=2,
                                    padding='VALID', scope='Conv2d_1a_3x3')
    with tf.variable_scope('Branch_3'):
        tower_pool = slim.max_pool2d(net, 3, stride=2, padding='VALID',
                                     scope='MaxPool_1a_3x3')
    net = tf.concat([tower_conv_1, tower_conv1_1,
                        tower_conv2_2, tower_pool], 3)
    return net 

def _build_network(self):
            
        with slim.arg_scope([slim.conv2d],
                        activation_fn=tf.nn.relu,
                        weights_regularizer=slim.l2_regularizer(self.weight_decay),
                        weights_initializer= self.weights_initializer,
                        biases_initializer = self.biases_initializer):
            with slim.arg_scope([slim.conv2d, slim.max_pool2d],
                                padding='SAME',
                                data_format = self.data_format):
                with tf.variable_scope(self.basenet_type):
                    basenet, end_points = net_factory.get_basenet(self.basenet_type, self.inputs);
                    
                with tf.variable_scope('extra_layers'):
                    self.net, self.end_points = self._add_extra_layers(basenet, end_points);
                
                with tf.variable_scope('seglink_layers'):
                    self._add_seglink_layers(); 

def _crop_pool_layer(self, bottom, rois, name):
    with tf.variable_scope(name) as scope:
      batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
      # Get the normalized coordinates of bboxes
      bottom_shape = tf.shape(bottom)
      height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
      width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
      x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
      y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
      x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
      y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
      # Won't be backpropagated to rois anyway, but to save time
      bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
      if cfg.RESNET.MAX_POOL:
        pre_pool_size = cfg.POOLING_SIZE * 2
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],
                                         name="crops")
        crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
      else:
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [cfg.POOLING_SIZE, cfg.POOLING_SIZE],
                                         name="crops")
    return crops

  # Do the first few layers manually, because 'SAME' padding can behave inconsistently
  # for images of different sizes: sometimes 0, sometimes 1 

def _crop_pool_layer(self, bottom, rois, name):
    with tf.variable_scope(name) as scope:
      batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
      # Get the normalized coordinates of bboxes
      bottom_shape = tf.shape(bottom)
      height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
      width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
      x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
      y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
      x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
      y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
      # Won't be backpropagated to rois anyway, but to save time
      bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
      pre_pool_size = cfg.POOLING_SIZE * 2
      crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size], name="crops")

    return slim.max_pool2d(crops, [2, 2], padding='SAME') 

def _image_to_head(self, is_training, reuse=None):
        with tf.variable_scope(self._scope, self._scope, reuse=reuse):
            net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3],
                              trainable=False, scope='conv1')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1')
            net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3],
                              trainable=False, scope='conv2')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2')
            net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3],
                              trainable=is_training, scope='conv3')
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3')

            net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3],
                              trainable=is_training, scope='conv4')
            self.end_points['conv4_3'] = net
            net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4')
            net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3],
                              trainable=is_training, scope='conv5')
            self.end_points['conv5_3'] = net
        self._act_summaries.append(net)
        self._layers['head'] = net 

def _crop_pool_layer(self, bottom, rois, name):
    with tf.variable_scope(name) as scope:
      batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
      # Get the normalized coordinates of bboxes
      bottom_shape = tf.shape(bottom)
      height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
      width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
      x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
      y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
      x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
      y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
      # Won't be backpropagated to rois anyway, but to save time
      bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
      if cfg.RESNET.MAX_POOL:
        pre_pool_size = cfg.POOLING_SIZE * 2
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],
                                         name="crops")
        crops = slim.max_pool2d(crops, [2, 2], padding='SAME')
      else:
        crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [cfg.POOLING_SIZE, cfg.POOLING_SIZE],
                                         name="crops")
    return crops

  # Do the first few layers manually, because 'SAME' padding can behave inconsistently
  # for images of different sizes: sometimes 0, sometimes 1 

def _crop_pool_layer(self, bottom, rois, name):
    with tf.variable_scope(name) as scope:
      batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])
      # Get the normalized coordinates of bboxes
      bottom_shape = tf.shape(bottom)
      height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])
      width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])
      x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / width
      y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
      x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
      y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height  #revised
      # Won't be backpropagated to rois anyway, but to save time
      bboxes = tf.stop_gradient(tf.concat(1,[y1, x1, y2, x2]))
      pre_pool_size = cfg.POOLING_SIZE * 2
      crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size], name="crops")

    return slim.max_pool2d(crops, [2, 2], padding='SAME') 

def _image_to_head(self, is_training, reuse=None):
        with slim.arg_scope(self._arg_scope(is_training, reuse)):
            net = slim.conv2d(self._image, 96, [3, 3], stride=1, scope='conv1')
            net = slim.max_pool2d(net, [2, 2], stride=2, scope='maxpool1')
            net = self.fire_module(net, 16, 64, scope='fire2')
            net = self.fire_module(net, 16, 64, scope='fire3')
            net = self.fire_module(net, 32, 128, scope='fire4')
            net = slim.max_pool2d(net, [2, 2], stride=2, scope='maxpool4')
            net = self.fire_module(net, 32, 128, scope='fire5')
            net = self.fire_module(net, 48, 192, scope='fire6')
            net = self.fire_module(net, 48, 192, scope='fire7')
            net = self.fire_module(net, 64, 256, scope='fire8')
            net = slim.max_pool2d(net, [2, 2], stride=2, scope='maxpool8', padding='SAME')
            net = self.fire_module(net, 64, 256, scope='fire9')
            net = slim.max_pool2d(net, [2, 2], stride=2, scope='maxpool9', padding='SAME')
            net = self.fire_module(net, 64, 512, scope='fire10')

        self._act_summaries.append(net)
        self._layers['head'] = net

        return net 

def subsample(inputs, factor, scope=None):
  """Subsamples the input along the spatial dimensions.

  Args:
    inputs: A `Tensor` of size [batch, height_in, width_in, channels].
    factor: The subsampling factor.
    scope: Optional variable_scope.

  Returns:
    output: A `Tensor` of size [batch, height_out, width_out, channels] with the
      input, either intact (if factor == 1) or subsampled (if factor > 1).
  """
  if factor == 1:
    return inputs
  else:
    return slim.max_pool2d(inputs, [1, 1], stride=factor, scope=scope) 

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

        return net 

def maxpool(x, kernel_size):
    p = np.floor((kernel_size - 1) / 2).astype(np.int32)
    p_x = tf.pad(x, [[0, 0], [p, p], [p, p], [0, 0]])
    return slim.max_pool2d(p_x, kernel_size) 

def R_Net(inputs,label=None,bbox_target=None,landmark_target=None,training=True):
    with slim.arg_scope([slim.conv2d],
                        activation_fn = prelu,
                        weights_initializer=slim.xavier_initializer(),
                        biases_initializer=tf.zeros_initializer(),
                        weights_regularizer=slim.l2_regularizer(0.0005),
                        padding='valid'):
        print( inputs.get_shape())
        net = slim.conv2d(inputs, num_outputs=28, kernel_size=[3,3], stride=1, scope="conv1")
        print( net.get_shape())
        net = slim.max_pool2d(net, kernel_size=[3, 3], stride=2, scope="pool1", padding='SAME')
        print( net.get_shape())
        net = slim.conv2d(net,num_outputs=48,kernel_size=[3,3],stride=1,scope="conv2")
        print( net.get_shape())
        net = slim.max_pool2d(net,kernel_size=[3,3],stride=2,scope="pool2")
        print( net.get_shape())
        net = slim.conv2d(net,num_outputs=64,kernel_size=[2,2],stride=1,scope="conv3")
        print( net.get_shape())
        fc_flatten = slim.flatten(net)
        print( fc_flatten.get_shape())
        fc1 = slim.fully_connected(fc_flatten, num_outputs=128,scope="fc1")
        print( fc1.get_shape())
        #batch*2
        cls_prob = slim.fully_connected(fc1,num_outputs=2,scope="cls_fc",activation_fn=tf.nn.softmax)
        print( cls_prob.get_shape())
        #batch*4
        bbox_pred = slim.fully_connected(fc1,num_outputs=4,scope="bbox_fc",activation_fn=None)
        print( bbox_pred.get_shape())
        #batch*10
        landmark_pred = slim.fully_connected(fc1,num_outputs=10,scope="landmark_fc",activation_fn=None)
        print( landmark_pred.get_shape())
        #train
        if training:
            cls_loss = cls_ohem(cls_prob,label)
            bbox_loss = bbox_ohem(bbox_pred,bbox_target,label)
            accuracy = cal_accuracy(cls_prob,label)
            landmark_loss = landmark_ohem(landmark_pred,landmark_target,label)
            L2_loss = tf.add_n(slim.losses.get_regularization_losses())
            return cls_loss,bbox_loss,landmark_loss,L2_loss,accuracy
        else:
            return cls_prob,bbox_pred,landmark_pred