def _instantiate_layers(self):
"""
定义两个全连接层和后面的分类回归层
:return: 无
"""
# We define layers as an array since they are simple fully connected
# ones and it should be easy to tune it from the network config.
# 定义两个全连接层, layer_size表示输出通道数
self._layers = [
snt.Linear(
layer_size,
name='fc_{}'.format(i),
initializers={'w': self._rcnn_initializer},
regularizers={'w': self.regularizer},
) for i, layer_size in enumerate(self._layer_sizes)
]
# We define the classifier layer having a num_classes + 1 background
# since we want to be able to predict if the proposal is background as
# well.
# 定义一个分类的全连接层(21类)
self._classifier_layer = snt.Linear(
self._num_classes + 1,
name='fc_classifier',
initializers={'w': self._cls_initializer},
regularizers={'w': self.regularizer},
)
# The bounding box adjustment layer has 4 times the number of classes
# We choose which to use depending on the output of the classifier
# layer
# 输出通道数为类别数目x4, 也就是4x20, 每个类别对应4个值, 这个是独立于分类器的输出
self._bbox_layer = snt.Linear(
self._num_classes * 4,
name='fc_bbox',
initializers={'w': self._bbox_initializer},
regularizers={'w': self.regularizer})
# ROIPoolingLayer is used to extract the feature from the feature map
# using the proposals.
# self._config.roi表示的就是选择crop, 7x7, valid的池化配置
self._roi_pool = ROIPoolingLayer(self._config.roi, debug=self._debug)
# RCNNTarget is used to define a minibatch and the correct values for
# each of the proposals.
# 用来定义minibatch和提案的正确值
self._rcnn_target = RCNNTarget(self._num_classes,
self._config.target,
variances=self._variances,
seed=self._seed)
# RCNNProposal generates the final bounding boxes and tries to remove
# duplicates.
self._rcnn_proposal = RCNNProposal(self._num_classes,
self._config.proposals,
variances=self._variances)
def _instantiate_layers(self):
# We define layers as an array since they are simple fully connected
# ones and it should be easy to tune it from the network config.
self._layers = [
snt.Linear(
layer_size,
name="fc_{}".format(i),
initializers={"w": self._rcnn_initializer},
regularizers={"w": self.regularizer},
)
for i, layer_size in enumerate(self._layer_sizes)
]
# We define the classifier layer having a num_classes + 1 background
# since we want to be able to predict if the proposal is background as
# well.
self._classifier_layer = snt.Linear(
self._num_classes + 1,
name="fc_classifier",
initializers={"w": self._cls_initializer},
regularizers={"w": self.regularizer},
)
# The bounding box adjustment layer has 4 times the number of classes
# We choose which to use depending on the output of the classifier
# layer
self._bbox_layer = snt.Linear(
self._num_classes * 4,
name="fc_bbox",
initializers={"w": self._bbox_initializer},
regularizers={"w": self.regularizer},
)
# ROIPoolingLayer is used to extract the feature from the feature map
# using the proposals.
self._roi_pool = ROIPoolingLayer(self._config.roi, debug=self._debug)
# RCNNTarget is used to define a minibatch and the correct values for
# each of the proposals.
self._rcnn_target = RCNNTarget(
self._num_classes,
self._config.target,
variances=self._variances,
seed=self._seed,
)
# RCNNProposal generates the final bounding boxes and tries to remove
# duplicates.
self._rcnn_proposal = RCNNProposal(
self._num_classes, self._config.proposals, variances=self._variances
)
def _run_roi_pooling(self, roi_proposals, pretrained, config):
roi_proposals_tf = tf.placeholder(
tf.float32, shape=roi_proposals.shape)
pretrained_tf = tf.placeholder(tf.float32, shape=pretrained.shape)
im_shape_tf = tf.placeholder(tf.float32, shape=(2,))
model = ROIPoolingLayer(config, debug=True)
results = model(roi_proposals_tf, pretrained_tf, im_shape_tf)
with self.test_session() as sess:
results = sess.run(results, feed_dict={
roi_proposals_tf: roi_proposals,
pretrained_tf: pretrained,
im_shape_tf: self.im_shape,
})
return results