卷积神经网络中feature map的含义

       在每个卷积层,数据都是以三维形式存在的。你可以把它看成许多个二维图片叠在一起,其中每一个称为一个feature map。在输入层,如果是灰度图片,那就只有一个feature map;如果是彩色图片,一般就是3个feature map(红绿蓝)。层与层之间会有若干个卷积核(kernel),上一层和每个feature map跟每个卷积核做卷积,都会产生下一层的一个feature map。

       多个Feature Map的作用是什么?

在卷积神经网络中,我们希望用一个网络模拟视觉通路的特性,分层的概念是自底向上构造简单到复杂的神经元。楼主关心的是同一层,那就说说同一层。
我们希望构造一组基,这组基能够形成对于一个事物完备的描述,例如描述一个人时我们通过描述身高/体重/相貌等,在卷积网中也是如此。在同一层,我们希望得到对于一张图片多种角度的描述,具体来讲就是用多种不同的卷积核对图像进行卷,得到不同核(这里的核可以理解为描述)上的响应,作为图像的特征。 他们的联系在于形成图像在同一层次不同基上的描述。下层的核主要是一些简单的边缘检测器(也可以理解为生理学上的simple cell)。


上层的核主要是一些简单核的叠加(或者用其他词更贴切),可以理解为complex cell。

多少个Feature Map?真的不好说,简单问题少,复杂问题多,但是自底向上一般是核的数量在逐渐变多(当然也有例外,如Alexnet),主要靠经验。

  • 4
    点赞
  • 36
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
The first CNN appeared in the work of Fukushima in 1980 and was called Neocognitron. The basic architectural ideas behind the CNN (local receptive fields,shared weights, and spatial or temporal subsampling) allow such networks to achieve some degree of shift and deformation invariance and at the same time reduce the number of training parameters. Since 1989, Yann LeCun and co-workers have introduced a series of CNNs with the general name LeNet, which contrary to the Neocognitron use supervised training. In this case, the major advantage is that the whole network is optimized for the given task, making this approach useable for real-world applications. LeNet has been successfully applied to character recognition, generic object recognition, face detection and pose estimation, obstacle avoidance in an autonomous robot etc. myCNN class allows to create, train and test generic convolutional networks (e.g., LeNet) as well as more general networks with features: - any directed acyclic graph can be used for connecting the layers of the network; - the network can have any number of arbitrarily sized input and output layers; - the neuron’s receptive field (RF) can have an arbitrary stride (step of local RF tiling), which means that in the S-layer, RFs can overlap and in the C-layer the stride can differ from 1; - any layer or feature map of the network can be switched from trainable to nontrainable (and vice versa) mode even during the training; - a new layer type: softmax-like M-layer. The archive contains the myCNN class source (with comments) and a simple example of LeNet5 creation and training. All updates and new releases can be found here: http://sites.google.com/site/chumerin/projects/mycnn

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值