如何为 yolo darknet cfg 文件提供两个输入?
我已经为yolov2 tiny开发了一个rgbd模型..所以它需要两个输入rgb和深度..分别提取特征并稍后加入层..在使用[route]时我无法获得两个输入
x = Conv2D(16, (3,3), strides=(1,1), padding='same', name='conv_1', use_bias=False)(input_image)
self.convLayers+=1
x = BatchNormalization(name='norm_1')(x)
x = LeakyReLU(alpha=0.1)(x)
Depthx = MaxPooling2D(pool_size=(2, 2))(x)
x = Conv2D(16, (3,3), strides=(1,1), padding='same', name='conv_2', use_bias=False)(input_image)
self.convLayers+=1
x = BatchNormalization(name='norm_1')(x)
x = LeakyReLU(alpha=0.1)(x)
Rgbx = MaxPooling2D(pool_size=(2, 2))(x)
# Fuse Layer
x = concatenate([Depthx, Rgbx])
x=Conv2D(16, (1,1), strides=(1,1), padding='same', name='conv_3', use_bias=False)(x)
self.convLayers+=1
x = BatchNormalization(name='norm_1')(x)
x = LeakyReLU(alpha=0.1)(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
我需要为此模型编写一个配置文件...欢迎任何有关配置文件编写的知识 提前致谢
I have developed a rgbd model for yolov2 tiny..So it requires two inputs rgb and depth ..feature extraction seperately and join the layer later..On using [route] I cannot get two inputs
x = Conv2D(16, (3,3), strides=(1,1), padding='same', name='conv_1', use_bias=False)(input_image)
self.convLayers+=1
x = BatchNormalization(name='norm_1')(x)
x = LeakyReLU(alpha=0.1)(x)
Depthx = MaxPooling2D(pool_size=(2, 2))(x)
x = Conv2D(16, (3,3), strides=(1,1), padding='same', name='conv_2', use_bias=False)(input_image)
self.convLayers+=1
x = BatchNormalization(name='norm_1')(x)
x = LeakyReLU(alpha=0.1)(x)
Rgbx = MaxPooling2D(pool_size=(2, 2))(x)
# Fuse Layer
x = concatenate([Depthx, Rgbx])
x=Conv2D(16, (1,1), strides=(1,1), padding='same', name='conv_3', use_bias=False)(x)
self.convLayers+=1
x = BatchNormalization(name='norm_1')(x)
x = LeakyReLU(alpha=0.1)(x)
x = MaxPooling2D(pool_size=(2, 2))(x)
I need to write a config file for this model...Any kind of knowledge in config file writing is welcome
Thanks in advance
如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱,如果其他用户或者作者回复了您的评论,将不能在第一时间通知您!
发布评论