def fpn_classifier_graph(rois,
feature_maps,
image_meta,
pool_size,
num_classes,
train_bn=True,
fc_layers_size=1024):
#---------------------------------------------------------------#
# ROI Pooling，利用建议框在特征层上进行截取
# x : [batch, num_rois, POOL_SIZE, POOL_SIZE, channels]
#---------------------------------------------------------------#
x = PyramidROIAlign([pool_size, pool_size],
name="roi_align_classifier")([rois, image_meta] +
feature_maps)
#------------------------------------------------------------------#
# 利用卷积进行特征整合
# x : [batch, num_rois, 1, 1, fc_layers_size]
#------------------------------------------------------------------#
x = TimeDistributed(Conv2D(fc_layers_size, (pool_size, pool_size),
padding="valid"),
name="mrcnn_class_conv1")(x)
x = TimeDistributed(BatchNormalization(),
name='mrcnn_class_bn1')(x, training=train_bn)
x = Activation('relu')(x)
#------------------------------------------------------------------#
# x : [batch, num_rois, 1, 1, fc_layers_size]
#------------------------------------------------------------------#
x = TimeDistributed(Conv2D(fc_layers_size, (1, 1)),
name="mrcnn_class_conv2")(x)
x = TimeDistributed(BatchNormalization(),
name='mrcnn_class_bn2')(x, training=train_bn)
x = Activation('relu')(x)
#------------------------------------------------------------------#
# x : [batch, num_rois, fc_layers_size]
#------------------------------------------------------------------#
shared = Lambda(lambda x: K.squeeze(K.squeeze(x, 3), 2),
name="pool_squeeze")(x)
#------------------------------------------------------------------#
# Classifier head
# 这个的预测结果代表这个先验框内部的物体的种类
# mrcnn_probs : [batch, num_rois, num_classes]
#------------------------------------------------------------------#
mrcnn_class_logits = TimeDistributed(Dense(num_classes),
name='mrcnn_class_logits')(shared)
mrcnn_probs = TimeDistributed(Activation("softmax"),
name="mrcnn_class")(mrcnn_class_logits)
#------------------------------------------------------------------#
# BBox head
# 这个的预测结果会对先验框进行调整
# mrcnn_bbox : [batch, num_rois, num_classes, 4]
#------------------------------------------------------------------#
x = TimeDistributed(Dense(num_classes * 4, activation='linear'),
name='mrcnn_bbox_fc')(shared)
mrcnn_bbox = Reshape((-1, num_classes, 4), name="mrcnn_bbox")(x)
return mrcnn_class_logits, mrcnn_probs, mrcnn_bbox
def build_fpn_mask_graph(rois,
feature_maps,
image_meta,
pool_size,
num_classes,
train_bn=True):
# ROI Pooling，利用建议框在特征层上进行截取
# 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)
# Shape: [batch, num_rois, MASK_POOL_SIZE, MASK_POOL_SIZE, channels]
x = TimeDistributed(Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv1")(x)
x = TimeDistributed(BatchNormalization(),
name='mrcnn_mask_bn1')(x, training=train_bn)
x = Activation('relu')(x)
# Shape: [batch, num_rois, MASK_POOL_SIZE, MASK_POOL_SIZE, channels]
x = TimeDistributed(Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv2")(x)
x = TimeDistributed(BatchNormalization(),
name='mrcnn_mask_bn2')(x, training=train_bn)
x = Activation('relu')(x)
# Shape: [batch, num_rois, MASK_POOL_SIZE, MASK_POOL_SIZE, channels]
x = TimeDistributed(Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv3")(x)
x = TimeDistributed(BatchNormalization(),
name='mrcnn_mask_bn3')(x, training=train_bn)
x = Activation('relu')(x)
# Shape: [batch, num_rois, MASK_POOL_SIZE, MASK_POOL_SIZE, channels]
x = TimeDistributed(Conv2D(256, (3, 3), padding="same"),
name="mrcnn_mask_conv4")(x)
x = TimeDistributed(BatchNormalization(),
name='mrcnn_mask_bn4')(x, training=train_bn)
x = Activation('relu')(x)
# Shape: [batch, num_rois, 2xMASK_POOL_SIZE, 2xMASK_POOL_SIZE, channels]
x = TimeDistributed(Conv2DTranspose(256, (2, 2),
strides=2,
activation="relu"),
name="mrcnn_mask_deconv")(x)
# 反卷积后再次进行一个1x1卷积调整通道，使其最终数量为numclasses，代表分的类
x = TimeDistributed(Conv2D(num_classes, (1, 1),
strides=1,
activation="sigmoid"),
name="mrcnn_mask")(x)
return x
def fpn_classifier_graph(
rois,
feature_maps,
image_meta,
pool_size,
num_classes,
train_bn=True,
fc_layers_size=1024): # pool_size调整后局部特征层的长宽，rois是建议框，image_meta保存图片信息
# ROI Pooling，利用建议框在特征层上进行截取[p2,p3,p4,p5]featureMap上截取
# Shape: [batch, num_rois, POOL_SIZE, POOL_SIZE, channels]
x = PyramidROIAlign([pool_size, pool_size], name="roi_align_classifier")(
[rois, image_meta] + feature_maps) # x是抠图
# Shape: [batch, num_rois, 1, 1, fc_layers_size]，相当于两次全连接，对后三个维度进行卷积和标准化
x = TimeDistributed(Conv2D(fc_layers_size, (pool_size, pool_size),
padding="valid"),
name="mrcnn_class_conv1")(x) # eg: fc_layers_size=1024
x = TimeDistributed(BatchNormalization(),
name='mrcnn_class_bn1')(x, training=train_bn)
x = Activation('relu')(x)
# Shape: [batch, num_rois, 1, 1, fc_layers_size]
x = TimeDistributed(Conv2D(fc_layers_size, (1, 1)),
name="mrcnn_class_conv2")(x)
x = TimeDistributed(BatchNormalization(),
name='mrcnn_class_bn2')(x, training=train_bn)
x = Activation('relu')(x)
# Shape: [batch, num_rois, fc_layers_size]
shared = Lambda(lambda x: K.squeeze(K.squeeze(x, 3), 2),
name="pool_squeeze")(x)
# Classifier head
# 这个的预测结果代表这个先验框内部的物体的种类[batch, num_rois,num_classes]
mrcnn_class_logits = TimeDistributed(Dense(num_classes),
name='mrcnn_class_logits')(shared)
mrcnn_probs = TimeDistributed(Activation("softmax"),
name="mrcnn_class")(mrcnn_class_logits)
# BBox head
# 这个的预测结果会对先验框进行调整
# [batch, num_rois, NUM_CLASSES * (dy, dx, log(dh), log(dw))]
x = TimeDistributed(Dense(num_classes * 4, activation='linear'),
name='mrcnn_bbox_fc')(shared)
# Reshape to [batch, num_rois, NUM_CLASSES, (dy, dx, log(dh), log(dw))]
mrcnn_bbox = Reshape((-1, num_classes, 4), name="mrcnn_bbox")(x)
return mrcnn_class_logits, mrcnn_probs, mrcnn_bbox