Spaces:
Sleeping
Sleeping
File size: 9,705 Bytes
5672777 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 |
# Copyright 2023 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.
"""RetinaNet."""
from typing import Any, Mapping, List, Optional, Union, Sequence
# Import libraries
import tensorflow as tf, tf_keras
from official.vision.ops import anchor
@tf_keras.utils.register_keras_serializable(package='Vision')
class RetinaNetModel(tf_keras.Model):
"""The RetinaNet model class."""
def __init__(self,
backbone: tf_keras.Model,
decoder: tf_keras.Model,
head: tf_keras.layers.Layer,
detection_generator: tf_keras.layers.Layer,
min_level: Optional[int] = None,
max_level: Optional[int] = None,
num_scales: Optional[int] = None,
aspect_ratios: Optional[List[float]] = None,
anchor_size: Optional[float] = None,
**kwargs):
"""Detection initialization function.
Args:
backbone: `tf_keras.Model` a backbone network.
decoder: `tf_keras.Model` a decoder network.
head: `RetinaNetHead`, the RetinaNet head.
detection_generator: the detection generator.
min_level: Minimum level in output feature maps.
max_level: Maximum level in output feature maps.
num_scales: A number representing intermediate scales added
on each level. For instances, num_scales=2 adds one additional
intermediate anchor scales [2^0, 2^0.5] on each level.
aspect_ratios: A list representing the aspect raito
anchors added on each level. The number indicates the ratio of width to
height. For instances, aspect_ratios=[1.0, 2.0, 0.5] adds three anchors
on each scale level.
anchor_size: A number representing the scale of size of the base
anchor to the feature stride 2^level.
**kwargs: keyword arguments to be passed.
"""
super(RetinaNetModel, self).__init__(**kwargs)
self._config_dict = {
'backbone': backbone,
'decoder': decoder,
'head': head,
'detection_generator': detection_generator,
'min_level': min_level,
'max_level': max_level,
'num_scales': num_scales,
'aspect_ratios': aspect_ratios,
'anchor_size': anchor_size,
}
self._backbone = backbone
self._decoder = decoder
self._head = head
self._detection_generator = detection_generator
def call(self,
images: Union[tf.Tensor, Sequence[tf.Tensor]],
image_shape: Optional[tf.Tensor] = None,
anchor_boxes: Optional[Mapping[str, tf.Tensor]] = None,
output_intermediate_features: bool = False,
training: bool = None) -> Mapping[str, tf.Tensor]:
"""Forward pass of the RetinaNet model.
Args:
images: `Tensor` or a sequence of `Tensor`, the input batched images to
the backbone network, whose shape(s) is [batch, height, width, 3]. If it
is a sequence of `Tensor`, we will assume the anchors are generated
based on the shape of the first image(s).
image_shape: `Tensor`, the actual shape of the input images, whose shape
is [batch, 2] where the last dimension is [height, width]. Note that
this is the actual image shape excluding paddings. For example, images
in the batch may be resized into different shapes before padding to the
fixed size.
anchor_boxes: a dict of tensors which includes multilevel anchors.
- key: `str`, the level of the multilevel predictions.
- values: `Tensor`, the anchor coordinates of a particular feature
level, whose shape is [height_l, width_l, num_anchors_per_location].
output_intermediate_features: `bool` indicating whether to return the
intermediate feature maps generated by backbone and decoder.
training: `bool`, indicating whether it is in training mode.
Returns:
scores: a dict of tensors which includes scores of the predictions.
- key: `str`, the level of the multilevel predictions.
- values: `Tensor`, the box scores predicted from a particular feature
level, whose shape is
[batch, height_l, width_l, num_classes * num_anchors_per_location].
boxes: a dict of tensors which includes coordinates of the predictions.
- key: `str`, the level of the multilevel predictions.
- values: `Tensor`, the box coordinates predicted from a particular
feature level, whose shape is
[batch, height_l, width_l, 4 * num_anchors_per_location].
attributes: a dict of (attribute_name, attribute_predictions). Each
attribute prediction is a dict that includes:
- key: `str`, the level of the multilevel predictions.
- values: `Tensor`, the attribute predictions from a particular
feature level, whose shape is
[batch, height_l, width_l, att_size * num_anchors_per_location].
"""
outputs = {}
# Feature extraction.
features = self.backbone(images)
if output_intermediate_features:
outputs.update(
{'backbone_{}'.format(k): v for k, v in features.items()})
if self.decoder:
features = self.decoder(features)
if output_intermediate_features:
outputs.update(
{'decoder_{}'.format(k): v for k, v in features.items()})
# Dense prediction. `raw_attributes` can be empty.
raw_scores, raw_boxes, raw_attributes = self.head(features)
if training:
outputs.update({
'cls_outputs': raw_scores,
'box_outputs': raw_boxes,
})
if raw_attributes:
outputs.update({'attribute_outputs': raw_attributes})
return outputs
else:
# Generate anchor boxes for this batch if not provided.
if anchor_boxes is None:
if isinstance(images, Sequence):
primary_images = images[0]
elif isinstance(images, tf.Tensor):
primary_images = images
else:
raise ValueError(
'Input should be a tf.Tensor or a sequence of tf.Tensor, not {}.'
.format(type(images)))
_, image_height, image_width, _ = primary_images.get_shape().as_list()
anchor_boxes = anchor.Anchor(
min_level=self._config_dict['min_level'],
max_level=self._config_dict['max_level'],
num_scales=self._config_dict['num_scales'],
aspect_ratios=self._config_dict['aspect_ratios'],
anchor_size=self._config_dict['anchor_size'],
image_size=(image_height, image_width)).multilevel_boxes
for l in anchor_boxes:
anchor_boxes[l] = tf.tile(
tf.expand_dims(anchor_boxes[l], axis=0),
[tf.shape(primary_images)[0], 1, 1, 1])
# Post-processing.
final_results = self.detection_generator(raw_boxes, raw_scores,
anchor_boxes, image_shape,
raw_attributes)
outputs.update({
'cls_outputs': raw_scores,
'box_outputs': raw_boxes,
})
def _update_decoded_results():
outputs.update({
'decoded_boxes': final_results['decoded_boxes'],
'decoded_box_scores': final_results['decoded_box_scores'],
})
if final_results.get('decoded_box_attributes') is not None:
outputs['decoded_box_attributes'] = final_results[
'decoded_box_attributes'
]
if self.detection_generator.get_config()['apply_nms']:
outputs.update({
'detection_boxes': final_results['detection_boxes'],
'detection_scores': final_results['detection_scores'],
'detection_classes': final_results['detection_classes'],
'num_detections': final_results['num_detections'],
})
# Users can choose to include the decoded results (boxes before NMS) in
# the output tensor dict even if `apply_nms` is set to `True`.
if self.detection_generator.get_config()['return_decoded']:
_update_decoded_results()
else:
_update_decoded_results()
if raw_attributes:
outputs.update({
'attribute_outputs': raw_attributes,
'detection_attributes': final_results['detection_attributes'],
})
return outputs
@property
def checkpoint_items(
self) -> Mapping[str, Union[tf_keras.Model, tf_keras.layers.Layer]]:
"""Returns a dictionary of items to be additionally checkpointed."""
items = dict(backbone=self.backbone, head=self.head)
if self.decoder is not None:
items.update(decoder=self.decoder)
return items
@property
def backbone(self) -> tf_keras.Model:
return self._backbone
@property
def decoder(self) -> tf_keras.Model:
return self._decoder
@property
def head(self) -> tf_keras.layers.Layer:
return self._head
@property
def detection_generator(self) -> tf_keras.layers.Layer:
return self._detection_generator
def get_config(self) -> Mapping[str, Any]:
return self._config_dict
@classmethod
def from_config(cls, config):
return cls(**config)
|