试用软件

How to add hand-crafted features as an input to a CNN model in MATLAB

12 次查看（过去 30 天）

显示更早的评论

Aasim 2022-5-8

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1714175-how-to-add-hand-crafted-features-as-an-input-to-a-cnn-model-in-matlab

评论： David Willingham 2022-5-26

采纳的回答： David Willingham

I have extracted hand-crafted features for a face image dataset and now I want to feed these feature vectors to a CNN model, so as to improve my image retrieval accuracy. Please guide me in this regard. Thank you.

7 个评论
显示 5更早的评论隐藏 5更早的评论

Abolfazl Chaman Motlagh 2022-5-24

do you have specific network architecture for your problem? because generally adding this extra feature to network has a lot of ambiguities. for example in which level of information (layer) you want to input these data to network?

Aasim 2022-5-24

I am using a pre-trained model Vgg-face

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

David Willingham 2022-5-24

2
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1714175-how-to-add-hand-crafted-features-as-an-input-to-a-cnn-model-in-matlab#answer_970845

Hi,

This example shows how to train a model using image and feature data, Train Network on Image and Feature Data.

Is this what you were looking for?

5 个评论
显示 3更早的评论隐藏 3更早的评论

Aasim 2022-5-26

Can you suggest me best tool to reconstruct images from the feature vectors?

David Willingham 2022-5-26

Has the network already been trained? If it requires re-training, why does the example above not suffice?

请先登录，再进行评论。

更多回答（0 个）

请先登录，再回答此问题。

类别

Image Processing and Computer Vision Computer Vision Toolbox Recognition, Object Detection, and Semantic Segmentation

在 Help Center 和 File Exchange 中查找有关 Recognition, Object Detection, and Semantic Segmentation 的更多信息

标签

产品

版本

R2021a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Translated by

试用软件