如何在CNN Caffemodel中将4096维特征向量缩减为1024维向量? [英] How do I reduce 4096-dimensional feature vector to 1024-dimensional vector in CNN Caffemodel?

问题描述

我使用16层VGGnet从图像中提取特征.它输出4096维特征向量.但是，我需要一个1024维向量.如何将这个4096个向量进一步缩减为1024个向量?我是否需要在fc7之上添加一个新层?

I used 16-layers VGGnet to extract features from an image. It outputs a 4096-dimensional feature vector. However, I need a 1024-dimensional vector. How do I further reduce this 4096-vector into 1024-vector? Do I need to add a new layer on top of fc7?

推荐答案

是的，您需要在fc7之上添加另一层.这就是最后几层的样子

Yes, you need to add another layer on top of fc7. This is how your last few layers should be like

layers {
  bottom: "fc7"
  top: "fc7"
  name: "relu7"
  type: RELU
}
layers {
  bottom: "fc7"
  top: "fc7"
  name: "drop7"
  type: DROPOUT
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc8"
  bottom: "fc7"
  top: "fc8"
  type: INNER_PRODUCT
  inner_product_param {
    num_output: 1024
  }
  blobs_lr: 0
  blobs_lr: 0
}
layers {
  name: "loss"
  type: SOFTMAX_LOSS
  bottom: "fc8"
  bottom: "label"
  top: "loss/loss"
}
layers {
  name: "accuracy/top1"
  type: ACCURACY
  bottom: "fc8"
  bottom: "label"
  top: "accuracy@1"
  include: { phase: TEST }
  accuracy_param {
    top_k: 1
  }
}

这篇关于如何在CNN Caffemodel中将4096维特征向量缩减为1024维向量?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！