File size: 5,464 Bytes
9a393e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
# Copyright 2017 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

"""SSDFeatureExtractor for MobilenetV1 features."""

import tensorflow as tf

from object_detection.meta_architectures import ssd_meta_arch
from object_detection.models import feature_map_generators
from object_detection.utils import context_manager
from object_detection.utils import ops
from object_detection.utils import shape_utils
from nets import mobilenet_v1

slim = tf.contrib.slim


class SSDMobileNetV1FeatureExtractor(ssd_meta_arch.SSDFeatureExtractor):
  """SSD Feature Extractor using MobilenetV1 features."""

  def __init__(self,
               is_training,
               depth_multiplier,
               min_depth,
               pad_to_multiple,
               conv_hyperparams_fn,
               reuse_weights=None,
               use_explicit_padding=False,
               use_depthwise=False,
               override_base_feature_extractor_hyperparams=False):
    """MobileNetV1 Feature Extractor for SSD Models.

    Args:
      is_training: whether the network is in training mode.
      depth_multiplier: float depth multiplier for feature extractor.
      min_depth: minimum feature extractor depth.
      pad_to_multiple: the nearest multiple to zero pad the input height and
        width dimensions to.
      conv_hyperparams_fn: A function to construct tf slim arg_scope for conv2d
        and separable_conv2d ops in the layers that are added on top of the
        base feature extractor.
      reuse_weights: Whether to reuse variables. Default is None.
      use_explicit_padding: Use 'VALID' padding for convolutions, but prepad
        inputs so that the output dimensions are the same as if 'SAME' padding
        were used.
      use_depthwise: Whether to use depthwise convolutions. Default is False.
      override_base_feature_extractor_hyperparams: Whether to override
        hyperparameters of the base feature extractor with the one from
        `conv_hyperparams_fn`.
    """
    super(SSDMobileNetV1FeatureExtractor, self).__init__(
        is_training=is_training,
        depth_multiplier=depth_multiplier,
        min_depth=min_depth,
        pad_to_multiple=pad_to_multiple,
        conv_hyperparams_fn=conv_hyperparams_fn,
        reuse_weights=reuse_weights,
        use_explicit_padding=use_explicit_padding,
        use_depthwise=use_depthwise,
        override_base_feature_extractor_hyperparams=
        override_base_feature_extractor_hyperparams)

  def preprocess(self, resized_inputs):
    """SSD preprocessing.

    Maps pixel values to the range [-1, 1].

    Args:
      resized_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.
    """
    return (2.0 / 255.0) * resized_inputs - 1.0

  def extract_features(self, preprocessed_inputs):
    """Extract features from preprocessed inputs.

    Args:
      preprocessed_inputs: a [batch, height, width, channels] float tensor
        representing a batch of images.

    Returns:
      feature_maps: a list of tensors where the ith tensor has shape
        [batch, height_i, width_i, depth_i]
    """
    preprocessed_inputs = shape_utils.check_min_image_dim(
        33, preprocessed_inputs)

    feature_map_layout = {
        'from_layer': ['Conv2d_11_pointwise', 'Conv2d_13_pointwise', '', '',
                       '', ''],
        'layer_depth': [-1, -1, 512, 256, 256, 128],
        'use_explicit_padding': self._use_explicit_padding,
        'use_depthwise': self._use_depthwise,
    }

    with tf.variable_scope('MobilenetV1',
                           reuse=self._reuse_weights) as scope:
      with slim.arg_scope(
          mobilenet_v1.mobilenet_v1_arg_scope(
              is_training=None, regularize_depthwise=True)):
        with (slim.arg_scope(self._conv_hyperparams_fn())
              if self._override_base_feature_extractor_hyperparams
              else context_manager.IdentityContextManager()):
          _, image_features = mobilenet_v1.mobilenet_v1_base(
              ops.pad_to_multiple(preprocessed_inputs, self._pad_to_multiple),
              final_endpoint='Conv2d_13_pointwise',
              min_depth=self._min_depth,
              depth_multiplier=self._depth_multiplier,
              use_explicit_padding=self._use_explicit_padding,
              scope=scope)
      with slim.arg_scope(self._conv_hyperparams_fn()):
        feature_maps = feature_map_generators.multi_resolution_feature_maps(
            feature_map_layout=feature_map_layout,
            depth_multiplier=self._depth_multiplier,
            min_depth=self._min_depth,
            insert_1x1_conv=True,
            image_features=image_features)

    return feature_maps.values()