其他分享
首页 > 其他分享> > 目标检测—6 M2dNet

目标检测—6 M2dNet

作者:互联网

M2dNet


M2dNet用TUM模块进行多次特征提取,利用FFM模块进行特征融合,又添加注意力机制增强模型特征提取能力。

1 主干网络

1.1 C3, C4, C5 = VGG16(inputs).outputs[1:]  # 提取基本特征
2.1 base_feature = FFMv1(C4, C5, feature_size_1=256, feature_size_2=512)
2.2 feature_pyramid = _create_feature_pyramid(base_feature, stage=4) # 图像金字塔
2.3 outputs = SFAM(feature_pyramid,feature_pyramid_sizes)  # 注意力机制
3.1 classification = keras.layers.Conv2D(filters=num_classes * num_anchors,kernel_size=3,strides=1,padding='same')(feature) # 预测类别
3.2 regression = keras.layers.Conv2D(filters=num_anchors * 4,kernel_size=3,strides=1,padding='same')(feature)  # 预测偏移

2 预测


3 训练


4 评估


标签:kernel,pyramid,检测,feature,目标,num,M2dNet,size
来源: https://blog.csdn.net/qq_35732321/article/details/114366596