模型结构
1、 FPN结构
在文档模型的输入与数据加载中，解析了模型的输入，并详细解析了模型是如何通过labelme标注的数据来生成这些输入。解析完模型输入之后，接下来便是FPN网络，即特征金字塔网络。
特征金字塔网络主要用于提取特征。通常的卷积网络是不断地堆叠卷积层然后利用最后一个卷积层的输出来进行分类等操作，而这种方法对于要识别图像中的小目标来说效果不是很好。为了解决这个问题使用特征金字塔网络，它在传统的卷积上多了一步上采样，将卷积的结果进行上采样，上采样的次数与卷积的次数相对应。大致示意如下图：
特征金字塔网络示意
和FPN网络相关的代码如下：
if callable(config.BACKBONE):
_, C2, C3, C4, C5 = config.BACKBONE(input_image, stage5=True,
train_bn=config.TRAIN_BN)
else:
_, C2, C3, C4, C5 = resnet_graph(input_image, config.BACKBONE,
stage5=True, train_bn=config.TRAIN_BN)
# Top-down Layers
# TODO: add assert to varify feature map sizes match what's in config
P5 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c5p5')(C5)
P4 = KL.Add(name="fpn_p4add")([
KL.UpSampling2D(size=(2, 2), name="fpn_p5upsampled")(P5),
KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c4p4')(C4)])
P3 = KL.Add(name="fpn_p3add")([
KL.UpSampling2D(size=(2, 2), name="fpn_p4upsampled")(P4),
KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c3p3')(C3)])
P2 = KL.Add(name="fpn_p2add")([
KL.UpSampling2D(size=(2, 2), name="fpn_p3upsampled")(P3),
KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c2p2')(C2)])
# Attach 3x3 conv to all P layers to get the final feature maps.
P2 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p2")(P2)
P3 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p3")(P3)
P4 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p4")(P4)
P5 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p5")(P5)
# P6 is used for the 5th anchor scale in RPN. Generated by
# subsampling from P5 with stride of 2.
P6 = KL.MaxPooling2D(pool_size=(1, 1), strides=2, name="fpn_p6")(P5)
# Note that P6 is used in RPN, but not in the classifier heads.
rpn_feature_maps = [P2, P3, P4, P5, P6]
mrcnn_feature_maps = [P2, P3, P4, P5]首先是第2行到第7行的if语句，这里主要是根据配置来选择主干网络，默认情况下是使用resnet101网络，执行的是第6行的resnet_graph方法。该方法内容如下：
def resnet_graph(input_image, architecture, stage5=False, train_bn=True):
"""Build a ResNet graph.
architecture: Can be resnet50 or resnet101
stage5: Boolean. If False, stage5 of the network is not created
train_bn: Boolean. Train or freeze Batch Norm layers
"""
assert architecture in ["resnet50", "resnet101"]
# Stage 1
x = KL.ZeroPadding2D((3, 3))(input_image)
x = KL.Conv2D(64, (7, 7), strides=(2, 2), name='conv1', use_bias=True)(x)
x = BatchNorm(name='bn_conv1')(x, training=train_bn)
x = KL.Activation('relu')(x)
C1 = x = KL.MaxPooling2D((3, 3), strides=(2, 2), padding="same")(x)
# Stage 2
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1), train_bn=train_bn)
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b', train_bn=train_bn)
C2 = x = identity_block(x, 3, [64, 64, 256], stage=2, block='c', train_bn=train_bn)
# Stage 3
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a', train_bn=train_bn)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b', train_bn=train_bn)
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c', train_bn=train_bn)
C3 = x = identity_block(x, 3, [128, 128, 512], stage=3, block='d', train_bn=train_bn)
# Stage 4
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a', train_bn=train_bn)
block_count = {"resnet50": 5, "resnet101": 22}[architecture]
for i in range(block_count):
x = identity_block(x, 3, [256, 256, 1024], stage=4, block=chr(98 + i), train_bn=train_bn)
C4 = x
# Stage 5
if stage5:
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a', train_bn=train_bn)
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b', train_bn=train_bn)
C5 = x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c', train_bn=train_bn)
else:
C5 = None
return [C1, C2, C3, C4, C5]这个方法主要是实现了resnet网络。resnet网络最重要的是提出了一种叫残差网络的结构，残差网络结构示意如下图：
残差网络示意
如上图所示，残差网络会将输入分成两条线，其中一条线会执行三个卷积（即图中三个框代表的卷积层），然后执行的结果与另一条线的结果（即上图右边的线，这里什么都没做，其结果即为输入）相加。
残差网络实际有两种结果，一种为conv_block，另一种为identity_block。其中identity_block和上图类似直接将卷积的结果与输入相加，而conv_block则是在右边的线上同样执行了一个1*1的卷积。
了解了残差网络后再来细看其实现resnet的resnet_graph方法。
因为这里的resnet实际是要用来构建特征金字塔网络的，所以这里并不是直接输出最终卷积的结果，而是输出了卷积过程中的五个特征层。
首先是第9行到第13行，这里输出第一个特征层：C1。这个特征层实际在后续的特征金字塔中并没有被使用。这里首先是第9行对图片的周围进行填充，这是因为卷积会改变图片的形状，填充可以保持图片的形状不变。然后是第10行设置一个卷积核为7*7的卷积层。这里的步长设置为2，图片的形状会被压缩一半。然后是第11行设置一个标准化层，第12行设置激活函数层。这两层基本是必定会出现在卷积层后的。最后是第13行设置了一个最大池化层，这里的步长也被设置成了2，图像会被再次压缩一半。
然后是第15到第17行，这里会输出第二个特征层：C2。这里很简单，就是执行了一个conv_block和两个identity_block。这里执行conv_block的时候将步长设置为了1，所以这里不会改变图片的形状。
然后是第19行到第22行，这里会输出第三个特征层：C3。这里与C2类似，执行了一个conv_block和三个identity_block。这里的conv_block的步长是2，他会将图片再次压缩一半。
然后是第24行到第28行，这里会输出第四个特征层：C4。这里和上述的操作类似，只是会根据使用的模型是resnet101还是resnet50来执行不同个数的identity_block。这里的conv_block的步长是2，他会将图片再次压缩一半。
最后是第30到第35行，这里输出第五个特征层：C5。这里与上述操作类似。
这里再细看残差网络的conv_block和identity_block的实现方式，首先是conv_block，其内容如下：
def conv_block(input_tensor, kernel_size, filters, stage, block,
strides=(2, 2), use_bias=True, train_bn=True):
"""conv_block is the block that has a conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: default 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
use_bias: Boolean. To use or not use a bias in conv layers.
train_bn: Boolean. Train or freeze Batch Norm layers
Note that from stage 3, the first conv layer at main path is with subsample=(2,2)
And the shortcut should have subsample=(2,2) as well
"""
nb_filter1, nb_filter2, nb_filter3 = filters
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = KL.Conv2D(nb_filter1, (1, 1), strides=strides,
name=conv_name_base + '2a', use_bias=use_bias)(input_tensor)
x = BatchNorm(name=bn_name_base + '2a')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter2, (kernel_size, kernel_size), padding='same',
name=conv_name_base + '2b', use_bias=use_bias)(x)
x = BatchNorm(name=bn_name_base + '2b')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base +
'2c', use_bias=use_bias)(x)
x = BatchNorm(name=bn_name_base + '2c')(x, training=train_bn)
shortcut = KL.Conv2D(nb_filter3, (1, 1), strides=strides,
name=conv_name_base + '1', use_bias=use_bias)(input_tensor)
shortcut = BatchNorm(name=bn_name_base + '1')(shortcut, training=train_bn)
x = KL.Add()([x, shortcut])
x = KL.Activation('relu', name='res' + str(stage) + block + '_out')(x)
return x首先是第15行拆分三个卷积层的通道数，然后是第16行和第17行生成网络层的名称的前缀。然后是第19行到第22行，这里主要是一个11的卷积层、一个标准化层和一个激活函数层，这里的卷积层的步长是传入的strides参数。然后是第24行到第27行这里也是一个标准卷积模块，他的卷积核为传入的kernel_size。然后是第29到第31行，这里是一个11的卷积层和一个标准化层。然后是第33行到第35行，这里也是一个卷积模块，只是这个卷积的输入是方法输入的input，而不是上一层卷积的结果。最后是第37行到第38行，这里会将两条卷积线的结果相加，然后再接上一个激活函数层。
以上便是conv_block的主要内容，然后是identity_block，其内容如下：
def identity_block(input_tensor, kernel_size, filters, stage, block,
use_bias=True, train_bn=True):
"""The identity_block is the block that has no conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: default 3, the kernel size of middle conv layer at main path
filters: list of integers, the nb_filters of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
use_bias: Boolean. To use or not use a bias in conv layers.
train_bn: Boolean. Train or freeze Batch Norm layers
"""
nb_filter1, nb_filter2, nb_filter3 = filters
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = KL.Conv2D(nb_filter1, (1, 1), name=conv_name_base + '2a',
use_bias=use_bias)(input_tensor)
x = BatchNorm(name=bn_name_base + '2a')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter2, (kernel_size, kernel_size), padding='same',
name=conv_name_base + '2b', use_bias=use_bias)(x)
x = BatchNorm(name=bn_name_base + '2b')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.Conv2D(nb_filter3, (1, 1), name=conv_name_base + '2c',
use_bias=use_bias)(x)
x = BatchNorm(name=bn_name_base + '2c')(x, training=train_bn)
x = KL.Add()([x, input_tensor])
x = KL.Activation('relu', name='res' + str(stage) + block + '_out')(x)
return x这个模块和conv_block类似，主要区别在与第31行，这里是直接将卷积的结果和输入直接相加。
2、 RPN结构
RPN模型主要是调用build_rpn_model方法来创建的，调用代码如下：
这个方法内容如下：
def build_rpn_model(anchor_stride, anchors_per_location, depth):
input_feature_map = KL.Input(shape=[None, None, depth],
name="input_rpn_feature_map")
outputs = rpn_graph(input_feature_map, anchors_per_location, anchor_stride)
return KM.Model([input_feature_map], outputs, name="rpn_model")这里很简单，就三行代码。首先是第2行创建了一个输入层，然后是第4行调用rpn_graph方法创建模型主要结构，最后是第5行根据输入和输出来创建模型。
其中第4行调用的rpn_graph方法内容如下：
def rpn_graph(feature_map, anchors_per_location, anchor_stride):
shared = KL.Conv2D(512, (3, 3), padding='same', activation='relu',
strides=anchor_stride,
name='rpn_conv_shared')(feature_map)
# Anchor Score. [batch, height, width, anchors per location * 2].
x = KL.Conv2D(2 * anchors_per_location, (1, 1), padding='valid',
activation='linear', name='rpn_class_raw')(shared)
# Reshape to [batch, anchors, 2]
rpn_class_logits = KL.Lambda(
lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 2]))(x)
# Softmax on last dimension of BG/FG.
rpn_probs = KL.Activation(
"softmax", name="rpn_class_xxx")(rpn_class_logits)
# Bounding box refinement. [batch, H, W, anchors per location * depth]
# where depth is [x, y, log(w), log(h)]
x = KL.Conv2D(anchors_per_location * 4, (1, 1), padding="valid",
activation='linear', name='rpn_bbox_pred')(shared)
# Reshape to [batch, anchors, 4]
rpn_bbox = KL.Lambda(lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 4]))(x)
return [rpn_class_logits, rpn_probs, rpn_bbox]这段代码便是RPN代码的主要结构，首先是第2行，这里先用一个33的卷积层来处理输入，然后是用一个11的卷积层来缩减通道数，其通道数为2*anchors_per_location，这里的2代表的是分类数。在之前的文档中提到过rpn的输出有两个，其中一个是用来判断框中是否包含目标的概率，即这里的通道数中的2,这个2代表两个概率：一个包含的概率一个不包含的概率。然后是anchors_per_location，这个参数代表每个特征点上生成的先验框的个数，这个参数与生成先验框的方法相关。在mask rcnn中其为3。
然后是第11行将上面1*1的卷积输出reshape成[batch, anchors, 2]的形状。然后设置激活函数为softmax。
然后是第20行，再创建一个11的卷积层来缩减上面33卷积的输出。这里的通道数为anchors_per_location * 4，anchors_per_location与上面相同，这里的4代表先验框的调整参数，即之前提到的rpn的另一输出。最后的第24行同样是将输出reshape成[batch, anchors, 4]的形状。
3、 ROI层
在之前的文档中提到过ROI层主要的作用有两个：一个是根据rpn的结果和先验框来挑选建议框，另一个是根据建议框获取对应的特征。然后mask rcnn便可以根据这些特征来进行目标检测或者语义分割。
挑选建议框的代码如下：
这里主要是通过ProposalLayer层来实现的，这里是一个自定义的keras层，其内容如下：
class ProposalLayer(KE.Layer):
"""Receives anchor scores and selects a subset to pass as proposals
to the second stage. Filtering is done based on anchor scores and
non-max suppression to remove overlaps. It also applies bounding
box refinement deltas to anchors.
Inputs:
rpn_probs: [batch, num_anchors, (bg prob, fg prob)]
rpn_bbox: [batch, num_anchors, (dy, dx, log(dh), log(dw))]
anchors: [batch, num_anchors, (y1, x1, y2, x2)] anchors in normalized coordinates
Returns:
Proposals in normalized coordinates [batch, rois, (y1, x1, y2, x2)]
"""
def __init__(self, proposal_count, nms_threshold, config=None, **kwargs):
super(ProposalLayer, self).__init__(**kwargs)
self.config = config
self.proposal_count = proposal_count
self.nms_threshold = nms_threshold
def call(self, inputs):
# Box Scores. Use the foreground class confidence. [Batch, num_rois, 1]
scores = inputs[0][:, :, 1]
# Box deltas [batch, num_rois, 4]
deltas = inputs[1]
deltas = deltas * np.reshape(self.config.RPN_BBOX_STD_DEV, [1, 1, 4])
# Anchors
anchors = inputs[2]
# Improve performance by trimming to top anchors by score
# and doing the rest on the smaller subset.
pre_nms_limit = tf.minimum(self.config.PRE_NMS_LIMIT, tf.shape(anchors)[1])
ix = tf.nn.top_k(scores, pre_nms_limit, sorted=True,
name="top_anchors").indices
scores = utils.batch_slice([scores, ix], lambda x, y: tf.gather(x, y),
self.config.IMAGES_PER_GPU)
deltas = utils.batch_slice([deltas, ix], lambda x, y: tf.gather(x, y),
self.config.IMAGES_PER_GPU)
pre_nms_anchors = utils.batch_slice([anchors, ix], lambda a, x: tf.gather(a, x),
self.config.IMAGES_PER_GPU,
names=["pre_nms_anchors"])
# Apply deltas to anchors to get refined anchors.
# [batch, N, (y1, x1, y2, x2)]
boxes = utils.batch_slice([pre_nms_anchors, deltas],
lambda x, y: apply_box_deltas_graph(x, y),
self.config.IMAGES_PER_GPU,
names=["refined_anchors"])
# Clip to image boundaries. Since we're in normalized coordinates,
# clip to 0..1 range. [batch, N, (y1, x1, y2, x2)]
window = np.array([0, 0, 1, 1], dtype=np.float32)
boxes = utils.batch_slice(boxes,
lambda x: clip_boxes_graph(x, window),
self.config.IMAGES_PER_GPU,
names=["refined_anchors_clipped"])
# Filter out small boxes
# According to Xinlei Chen's paper, this reduces detection accuracy
# for small objects, so we're skipping it.
# Non-max suppression
def nms(boxes, scores):
indices = tf.image.non_max_suppression(
boxes, scores, self.proposal_count,
self.nms_threshold, name="rpn_non_max_suppression")
proposals = tf.gather(boxes, indices)
# Pad if needed
padding = tf.maximum(self.proposal_count - tf.shape(proposals)[0], 0)
print(padding)
proposals = tf.pad(proposals, [(0, padding), (0, 0)])
return proposals
proposals = utils.batch_slice([boxes, scores], nms,
self.config.IMAGES_PER_GPU)
return proposals
def compute_output_shape(self, input_shape):
return (None, self.proposal_count, 4)这里的重点是call方法，keras的自定义层的计算方法都是在call方法中实现的。这里的call方法有一个输入inputs，他即传入的[rpn_class, rpn_bbox, anchors]。
首先是第25行到第30行，这里主要是处理输入的参数。然后是第35行使用top_k方法取出概率最高的k个数，所在的索引。然后是第37行到第43行，根据这个索引取出对应概率值，先验框的调整参数和先验框。
然后是第47行到第50行根据，先验框和其调整参数来计算出建议框。然后是第54行到58行，上文计算获取的建议框，有可能会超出图片的范围，所以这里需要限制建议框，保证其在图片内。
最后是第77行对得到的建议框进行非极大抑制。
这便是ProposalLayer的主要内容，他主要是完成了ROI层的第一个作用，即根据rpn的输出和先验框来获取建议框。ROI的剩下一个作用：根据建议框获取特征是通过PyramidROIAlign层来实现的。这个层的内容如下：
class PyramidROIAlign(KE.Layer):
"""Implements ROI Pooling on multiple levels of the feature pyramid.
Params:
- pool_shape: [pool_height, pool_width] of the output pooled regions. Usually [7, 7]
Inputs:
- boxes: [batch, num_boxes, (y1, x1, y2, x2)] in normalized
coordinates. Possibly padded with zeros if not enough
boxes to fill the array.
- image_meta: [batch, (meta data)] Image details. See compose_image_meta()
- feature_maps: List of feature maps from different levels of the pyramid.
Each is [batch, height, width, channels]
Output:
Pooled regions in the shape: [batch, num_boxes, pool_height, pool_width, channels].
The width and height are those specific in the pool_shape in the layer
constructor.
"""
def __init__(self, pool_shape, **kwargs):
super(PyramidROIAlign, self).__init__(**kwargs)
self.pool_shape = tuple(pool_shape)
def call(self, inputs):
# Crop boxes [batch, num_boxes, (y1, x1, y2, x2)] in normalized coords
boxes = inputs[0]
# Image meta
# Holds details about the image. See compose_image_meta()
image_meta = inputs[1]
# Feature Maps. List of feature maps from different level of the
# feature pyramid. Each is [batch, height, width, channels]
feature_maps = inputs[2:]
# Assign each ROI to a level in the pyramid based on the ROI area.
y1, x1, y2, x2 = tf.split(boxes, 4, axis=2)
h = y2 - y1
w = x2 - x1
# Use shape of first image. Images in a batch must have the same size.
image_shape = parse_image_meta_graph(image_meta)['image_shape'][0]
# Equation 1 in the Feature Pyramid Networks paper. Account for
# the fact that our coordinates are normalized here.
# e.g. a 224x224 ROI (in pixels) maps to P4
image_area = tf.cast(image_shape[0] * image_shape[1], tf.float32)
roi_level = log2_graph(tf.sqrt(h * w) / (224.0 / tf.sqrt(image_area)))
roi_level = tf.minimum(5, tf.maximum(
2, 4 + tf.cast(tf.round(roi_level), tf.int32)))
roi_level = tf.squeeze(roi_level, 2)
# Loop through levels and apply ROI pooling to each. P2 to P5.
pooled = []
box_to_level = []
for i, level in enumerate(range(2, 6)):
ix = tf.where(tf.equal(roi_level, level))
level_boxes = tf.gather_nd(boxes, ix)
# Box indices for crop_and_resize.
box_indices = tf.cast(ix[:, 0], tf.int32)
# Keep track of which box is mapped to which level
box_to_level.append(ix)
# Stop gradient propogation to ROI proposals
level_boxes = tf.stop_gradient(level_boxes)
box_indices = tf.stop_gradient(box_indices)
# Crop and Resize
# From Mask R-CNN paper: "We sample four regular locations, so
# that we can evaluate either max or average pooling. In fact,
# interpolating only a single value at each bin center (without
# pooling) is nearly as effective."
#
# Here we use the simplified approach of a single value per bin,
# which is how it's done in tf.crop_and_resize()
# Result: [batch * num_boxes, pool_height, pool_width, channels]
pooled.append(tf.image.crop_and_resize(
feature_maps[i], level_boxes, box_indices, self.pool_shape,
method="bilinear"))
# Pack pooled features into one tensor
pooled = tf.concat(pooled, axis=0)
# Pack box_to_level mapping into one array and add another
# column representing the order of pooled boxes
box_to_level = tf.concat(box_to_level, axis=0)
box_range = tf.expand_dims(tf.range(tf.shape(box_to_level)[0]), 1)
box_to_level = tf.concat([tf.cast(box_to_level, tf.int32), box_range],
axis=1)
# Rearrange pooled features to match the order of the original boxes
# Sort box_to_level by batch then box index
# TF doesn't have a way to sort by two columns, so merge them and sort.
sorting_tensor = box_to_level[:, 0] * 100000 + box_to_level[:, 1]
ix = tf.nn.top_k(sorting_tensor, k=tf.shape(
box_to_level)[0]).indices[::-1]
ix = tf.gather(box_to_level[:, 2], ix)
pooled = tf.gather(pooled, ix)
# Re-add the batch dimension
shape = tf.concat([tf.shape(boxes)[:2], tf.shape(pooled)[1:]], axis=0)
pooled = tf.reshape(pooled, shape)
return pooled
def compute_output_shape(self, input_shape):
return input_shape[0][:2] + self.pool_shape + (input_shape[2][-1], )同上，其主要的代码也在call方法中。
首先是第27到35行，这里是在拆分输入的参数。一共有三个参数：boxes，image_meta,feature_maps。即：建议框、图片元数据、图片特征集合。然后是第38行到第40行计算建议框的宽高，然后是第46行到第50行根据建议框的面积来判断这个建议框对应的是那一个特征层的特征。然后是第55行到第80行，根据计算出的建议框对应的特征层，在该特征层中截取对应建议框位置的特征，并将特征resize到指定形状。最后将截取的特征转换成tensor，并按照boxes的顺序排序并返回。
4、 分类层
创建分类层调用的方法如下：
这个方法的详细内容如下：
def fpn_classifier_graph(rois, feature_maps, image_meta,
pool_size, num_classes, train_bn=True,
fc_layers_size=1024):
"""Builds the computation graph of the feature pyramid network classifier
and regressor heads.
rois: [batch, num_rois, (y1, x1, y2, x2)] Proposal boxes in normalized
coordinates.
feature_maps: List of feature maps from different layers of the pyramid,
[P2, P3, P4, P5]. Each has a different resolution.
image_meta: [batch, (meta data)] Image details. See compose_image_meta()
pool_size: The width of the square feature map generated from ROI Pooling.
num_classes: number of classes, which determines the depth of the results
train_bn: Boolean. Train or freeze Batch Norm layers
fc_layers_size: Size of the 2 FC layers
Returns:
logits: [batch, num_rois, NUM_CLASSES] classifier logits (before softmax)
probs: [batch, num_rois, NUM_CLASSES] classifier probabilities
bbox_deltas: [batch, num_rois, NUM_CLASSES, (dy, dx, log(dh), log(dw))] Deltas to apply to
proposal boxes
"""
# ROI Pooling
# Shape: [batch, num_rois, POOL_SIZE, POOL_SIZE, channels]
x = PyramidROIAlign([pool_size, pool_size],
name="roi_align_classifier")([rois, image_meta] + feature_maps)
# Two 1024 FC layers (implemented with Conv2D for consistency)
x = KL.TimeDistributed(KL.Conv2D(fc_layers_size, (pool_size, pool_size), padding="valid"),
name="mrcnn_class_conv1")(x)
x = KL.TimeDistributed(BatchNorm(), name='mrcnn_class_bn1')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.TimeDistributed(KL.Conv2D(fc_layers_size, (1, 1)),
name="mrcnn_class_conv2")(x)
x = KL.TimeDistributed(BatchNorm(), name='mrcnn_class_bn2')(x, training=train_bn)
x = KL.Activation('relu')(x)
shared = KL.Lambda(lambda x: K.squeeze(K.squeeze(x, 3), 2),
name="pool_squeeze")(x)
# Classifier head
mrcnn_class_logits = KL.TimeDistributed(KL.Dense(num_classes),
name='mrcnn_class_logits')(shared)
mrcnn_probs = KL.TimeDistributed(KL.Activation("softmax"),
name="mrcnn_class")(mrcnn_class_logits)
# BBox head
# [batch, num_rois, NUM_CLASSES * (dy, dx, log(dh), log(dw))]
x = KL.TimeDistributed(KL.Dense(num_classes * 4, activation='linear'),
name='mrcnn_bbox_fc')(shared)
# Reshape to [batch, num_rois, NUM_CLASSES, (dy, dx, log(dh), log(dw))]
s = K.int_shape(x)
mrcnn_bbox = KL.Reshape((s[1], num_classes, 4), name="mrcnn_bbox")(x)
return mrcnn_class_logits, mrcnn_probs, mrcnn_bbox首先是第25行创建的PyramidROIAlign层，这个层是上面解析的ROI的一个自定义层，主要作用是截取建议框特征。
然后是第28行到第35行，这里是两个卷积层结构，只不过在卷积层外添加了一个TimeDistributed层，这个层主要的作用是将输入的一个层应用于输入的每个时间片。以这里的卷积层为例：在PyramidROIAlign层返回的X的形状为[batch, num_rois, POOL_SIZE, POOL_SIZE, channels]。其中batch是批次数，num_rois是建议框数，pool_size是框的大小，channels是通道数。对于这种输入正常的卷积是对batch后的四个维度做卷积，而用TimeDistributed封装后的卷积只会对后面的三个维度做卷积。
然后是第37行使用squeeze方法降低维度，然后是第41行添加一个全连接层，全连接的输出维度即分类的类别数。然后是第43行对全连接的输出添加softmax激活函数。
然后是第48行再对缩减维度后的shared添加一个全连接层，这个全连接是用来预测目标框的，最后是51行和52行将处理目标框的输出。
5、 mask层
创建mask层调用的方法如下：
这个方法的内容如下：
def build_fpn_mask_graph(rois, feature_maps, image_meta,
pool_size, num_classes, train_bn=True):
"""Builds the computation graph of the mask head of Feature Pyramid Network.
rois: [batch, num_rois, (y1, x1, y2, x2)] Proposal boxes in normalized
coordinates.
feature_maps: List of feature maps from different layers of the pyramid,
[P2, P3, P4, P5]. Each has a different resolution.
image_meta: [batch, (meta data)] Image details. See compose_image_meta()
pool_size: The width of the square feature map generated from ROI Pooling.
num_classes: number of classes, which determines the depth of the results
train_bn: Boolean. Train or freeze Batch Norm layers
Returns: Masks [batch, num_rois, MASK_POOL_SIZE, MASK_POOL_SIZE, NUM_CLASSES]
"""
# ROI Pooling
# Shape: [batch, num_rois, MASK_POOL_SIZE, MASK_POOL_SIZE, channels]
x = PyramidROIAlign([pool_size, pool_size],
name="roi_align_mask")([rois, image_meta] + feature_maps)
# Conv layers
x = KL.TimeDistributed(KL.Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv1")(x)
x = KL.TimeDistributed(BatchNorm(),
name='mrcnn_mask_bn1')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.TimeDistributed(KL.Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv2")(x)
x = KL.TimeDistributed(BatchNorm(),
name='mrcnn_mask_bn2')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.TimeDistributed(KL.Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv3")(x)
x = KL.TimeDistributed(BatchNorm(),
name='mrcnn_mask_bn3')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.TimeDistributed(KL.Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv4")(x)
x = KL.TimeDistributed(BatchNorm(),
name='mrcnn_mask_bn4')(x, training=train_bn)
x = KL.Activation('relu')(x)
x = KL.TimeDistributed(KL.Conv2DTranspose(256, (2, 2), strides=2, activation="relu"),
name="mrcnn_mask_deconv")(x)
x = KL.TimeDistributed(KL.Conv2D(num_classes, (1, 1), strides=1, activation="sigmoid"),
name="mrcnn_mask")(x)
return x首先是第18行同样分类一样的PyramidROIAlign层，然后是22行到第44行，这里创建了4个33的卷积层结构。然后是第46行添加一个转置卷积，最后在添加一个11的卷积层。
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
