Python slim.conv2d方法代码示例

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def AddConvLayer(self, prev_layer, index):
    """Add a single standard convolutional 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'(C)(s|t|r|l|m)({\w+})?(\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(3))
    width = int(m.group(4))
    height = int(m.group(5))
    depth = int(m.group(6))
    fn = self._NonLinearity(m.group(2))
    return slim.conv2d(
        prev_layer, depth, [height, width], activation_fn=fn,
        scope=name), m.end() 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def model(image):
    image = mean_image_subtraction(image)
    with slim.arg_scope(vgg.vgg_arg_scope()):
        conv5_3 = vgg.vgg_16(image)

    rpn_conv = slim.conv2d(conv5_3, 512, 3)

    lstm_output = Bilstm(rpn_conv, 512, 128, 512, scope_name='BiLSTM')

    bbox_pred = lstm_fc(lstm_output, 512, 10 * 4, scope_name="bbox_pred")
    cls_pred = lstm_fc(lstm_output, 512, 10 * 2, scope_name="cls_pred")

    # transpose: (1, H, W, A x d) -> (1, H, WxA, d)
    cls_pred_shape = tf.shape(cls_pred)
    cls_pred_reshape = tf.reshape(cls_pred, [cls_pred_shape[0], cls_pred_shape[1], -1, 2])

    cls_pred_reshape_shape = tf.shape(cls_pred_reshape)
    cls_prob = tf.reshape(tf.nn.softmax(tf.reshape(cls_pred_reshape, [-1, cls_pred_reshape_shape[3]])),
                          [-1, cls_pred_reshape_shape[1], cls_pred_reshape_shape[2], cls_pred_reshape_shape[3]],
                          name="cls_prob")

    return bbox_pred, cls_pred, cls_prob 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def delf_attention(feature_map, config, is_training, arg_scope=None):
    with tf.variable_scope('attonly/attention/compute'):
        with slim.arg_scope(arg_scope):
            is_training = config['train_attention'] and is_training
            with slim.arg_scope([slim.conv2d, slim.batch_norm],
                                trainable=is_training):
                with slim.arg_scope([slim.batch_norm], is_training=is_training):
                    attention = slim.conv2d(
                            feature_map, 512, config['attention_kernel'], rate=1,
                            activation_fn=tf.nn.relu, scope='conv1')
                    attention = slim.conv2d(
                            attention, 1, config['attention_kernel'], rate=1,
                            activation_fn=None, normalizer_fn=None, scope='conv2')
                    attention = tf.nn.softplus(attention)
    if config['normalize_feature_map']:
        feature_map = tf.nn.l2_normalize(feature_map, -1)
    descriptor = tf.reduce_sum(feature_map*attention, axis=[1, 2])
    if config['normalize_average']:
        descriptor /= tf.reduce_sum(attention, axis=[1, 2])
    return descriptor 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def tower(image, mode, config):
        image = image_normalization(image)
        if image.shape[-1] == 1:
            image = tf.tile(image, [1, 1, 1, 3])

        with slim.arg_scope(resnet.resnet_arg_scope()):
            is_training = config['train_backbone'] and (mode == Mode.TRAIN)
            with slim.arg_scope([slim.conv2d, slim.batch_norm], trainable=is_training):
                _, encoder = resnet.resnet_v1_50(image,
                                                 is_training=is_training,
                                                 global_pool=False,
                                                 scope='resnet_v1_50')
        feature_map = encoder['resnet_v1_50/block3']

        if config['use_attention']:
            descriptor = delf_attention(feature_map, config, mode == Mode.TRAIN,
                                        resnet.resnet_arg_scope())
        else:
            descriptor = tf.reduce_max(feature_map, [1, 2])

        if config['dimensionality_reduction']:
            descriptor = dimensionality_reduction(descriptor, config)
        return descriptor 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def tower(image, mode, config):
        image = image_normalization(image)
        if image.shape[-1] == 1:
            image = tf.tile(image, [1, 1, 1, 3])

        with slim.arg_scope(resnet.resnet_arg_scope()):
            training = config['train_backbone'] and (mode == Mode.TRAIN)
            with slim.arg_scope([slim.conv2d, slim.batch_norm], trainable=training):
                _, encoder = resnet.resnet_v1_50(image,
                                                 is_training=training,
                                                 global_pool=False,
                                                 scope='resnet_v1_50')
        feature_map = encoder['resnet_v1_50/block3']
        descriptor = vlad(feature_map, config, mode == Mode.TRAIN)
        if config['dimensionality_reduction']:
            descriptor = dimensionality_reduction(descriptor, config)
        return descriptor 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
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 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def mobilenetv2_scope(is_training=True,
                      trainable=True,
                      weight_decay=0.00004,
                      stddev=0.09,
                      dropout_keep_prob=0.8,
                      bn_decay=0.997):
  """Defines Mobilenet training scope.
  In default. We do not use BN

  ReWrite the scope.
  """
  batch_norm_params = {
      'is_training': False,
      'trainable': False,
      'decay': bn_decay,
  }
  with slim.arg_scope(training_scope(is_training=is_training, weight_decay=weight_decay)):
      with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.separable_conv2d],
                          trainable=trainable):
          with slim.arg_scope([slim.batch_norm], **batch_norm_params) as sc:
              return sc 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def _build_aux_head(net, end_points, num_classes, hparams, scope):
  """Auxiliary head used for all models across all datasets."""
  with tf.variable_scope(scope):
    aux_logits = tf.identity(net)
    with tf.variable_scope('aux_logits'):
      aux_logits = slim.avg_pool2d(
          aux_logits, [5, 5], stride=3, padding='VALID')
      aux_logits = slim.conv2d(aux_logits, 128, [1, 1], scope='proj')
      aux_logits = slim.batch_norm(aux_logits, scope='aux_bn0')
      aux_logits = tf.nn.relu(aux_logits)
      # Shape of feature map before the final layer.
      shape = aux_logits.shape
      if hparams.data_format == 'NHWC':
        shape = shape[1:3]
      else:
        shape = shape[2:4]
      aux_logits = slim.conv2d(aux_logits, 768, shape, padding='VALID')
      aux_logits = slim.batch_norm(aux_logits, scope='aux_bn1')
      aux_logits = tf.nn.relu(aux_logits)
      aux_logits = contrib_layers.flatten(aux_logits)
      aux_logits = slim.fully_connected(aux_logits, num_classes)
      end_points['AuxLogits'] = aux_logits 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def _reduce_prev_layer(self, prev_layer, curr_layer):
    """Matches dimension of prev_layer to the curr_layer."""
    # Set the prev layer to the current layer if it is none
    if prev_layer is None:
      return curr_layer
    curr_num_filters = self._filter_size
    prev_num_filters = get_channel_dim(prev_layer.shape)
    curr_filter_shape = int(curr_layer.shape[2])
    prev_filter_shape = int(prev_layer.shape[2])
    if curr_filter_shape != prev_filter_shape:
      prev_layer = tf.nn.relu(prev_layer)
      prev_layer = factorized_reduction(prev_layer, curr_num_filters, stride=2)
    elif curr_num_filters != prev_num_filters:
      prev_layer = tf.nn.relu(prev_layer)
      prev_layer = slim.conv2d(
          prev_layer, curr_num_filters, 1, scope='prev_1x1')
      prev_layer = slim.batch_norm(prev_layer, scope='prev_bn')
    return prev_layer 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def _fixed_padding(inputs, kernel_size, rate=1):
  """Pads the input along the spatial dimensions independently of input size.

  Pads the input such that if it was used in a convolution with 'VALID' padding,
  the output would have the same dimensions as if the unpadded input was used
  in a convolution with 'SAME' padding.

  Args:
    inputs: A tensor of size [batch, height_in, width_in, channels].
    kernel_size: The kernel to be used in the conv2d or max_pool2d operation.
    rate: An integer, rate for atrous convolution.

  Returns:
    output: A tensor of size [batch, height_out, width_out, channels] with the
      input, either intact (if kernel_size == 1) or padded (if kernel_size > 1).
  """
  kernel_size_effective = [kernel_size[0] + (kernel_size[0] - 1) * (rate - 1),
                           kernel_size[0] + (kernel_size[0] - 1) * (rate - 1)]
  pad_total = [kernel_size_effective[0] - 1, kernel_size_effective[1] - 1]
  pad_beg = [pad_total[0] // 2, pad_total[1] // 2]
  pad_end = [pad_total[0] - pad_beg[0], pad_total[1] - pad_beg[1]]
  padded_inputs = tf.pad(inputs, [[0, 0], [pad_beg[0], pad_end[0]],
                                  [pad_beg[1], pad_end[1]], [0, 0]])
  return padded_inputs 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
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 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def _extra_conv_arg_scope(weight_decay=0.00001, activation_fn=None, normalizer_fn=None):

  with slim.arg_scope(
      [slim.conv2d, slim.conv2d_transpose],
      padding='SAME',
      weights_regularizer=slim.l2_regularizer(weight_decay),
      weights_initializer=tf.truncated_normal_initializer(stddev=0.001),
      activation_fn=activation_fn,
      normalizer_fn=normalizer_fn,) as arg_sc:
    with slim.arg_scope(
      [slim.fully_connected],
          weights_regularizer=slim.l2_regularizer(weight_decay),
          weights_initializer=tf.truncated_normal_initializer(stddev=0.001),
          activation_fn=activation_fn,
          normalizer_fn=normalizer_fn) as arg_sc:
          return arg_sc 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def block35(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
    """Builds the 35x35 resnet block."""
    with tf.variable_scope(scope, 'Block35', [net], reuse=reuse):
        with tf.variable_scope('Branch_0'):
            tower_conv = slim.conv2d(net, 32, 1, scope='Conv2d_1x1')
        with tf.variable_scope('Branch_1'):
            tower_conv1_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
            tower_conv1_1 = slim.conv2d(tower_conv1_0, 32, 3, scope='Conv2d_0b_3x3')
        with tf.variable_scope('Branch_2'):
            tower_conv2_0 = slim.conv2d(net, 32, 1, scope='Conv2d_0a_1x1')
            tower_conv2_1 = slim.conv2d(tower_conv2_0, 48, 3, scope='Conv2d_0b_3x3')
            tower_conv2_2 = slim.conv2d(tower_conv2_1, 64, 3, scope='Conv2d_0c_3x3')
        mixed = tf.concat([tower_conv, tower_conv1_1, tower_conv2_2], 3)
        up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
                         activation_fn=None, scope='Conv2d_1x1')
        net += scale * up
        if activation_fn:
            net = activation_fn(net)
    return net

# Inception-Resnet-B 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def block17(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
    """Builds the 17x17 resnet block."""
    with tf.variable_scope(scope, 'Block17', [net], reuse=reuse):
        with tf.variable_scope('Branch_0'):
            tower_conv = slim.conv2d(net, 192, 1, scope='Conv2d_1x1')
        with tf.variable_scope('Branch_1'):
            tower_conv1_0 = slim.conv2d(net, 128, 1, scope='Conv2d_0a_1x1')
            tower_conv1_1 = slim.conv2d(tower_conv1_0, 160, [1, 7],
                                        scope='Conv2d_0b_1x7')
            tower_conv1_2 = slim.conv2d(tower_conv1_1, 192, [7, 1],
                                        scope='Conv2d_0c_7x1')
        mixed = tf.concat([tower_conv, tower_conv1_2], 3)
        up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
                         activation_fn=None, scope='Conv2d_1x1')
        net += scale * up
        if activation_fn:
            net = activation_fn(net)
    return net


# Inception-Resnet-C 

# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d [as 别名]
def block8(net, scale=1.0, activation_fn=tf.nn.relu, scope=None, reuse=None):
    """Builds the 8x8 resnet block."""
    with tf.variable_scope(scope, 'Block8', [net], reuse=reuse):
        with tf.variable_scope('Branch_0'):
            tower_conv = slim.conv2d(net, 192, 1, scope='Conv2d_1x1')
        with tf.variable_scope('Branch_1'):
            tower_conv1_0 = slim.conv2d(net, 192, 1, scope='Conv2d_0a_1x1')
            tower_conv1_1 = slim.conv2d(tower_conv1_0, 224, [1, 3],
                                        scope='Conv2d_0b_1x3')
            tower_conv1_2 = slim.conv2d(tower_conv1_1, 256, [3, 1],
                                        scope='Conv2d_0c_3x1')
        mixed = tf.concat([tower_conv, tower_conv1_2], 3)
        up = slim.conv2d(mixed, net.get_shape()[3], 1, normalizer_fn=None,
                         activation_fn=None, scope='Conv2d_1x1')
        net += scale * up
        if activation_fn:
            net = activation_fn(net)
    return net