How to modify the fully connected layer for YOLO purposes?

7 次查看（过去 30 天）

Fahmi Akmal Dzulkifli 2023-2-7

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1907940-how-to-modify-the-fully-connected-layer-for-yolo-purposes

回答： Hornett 2024-9-25

Greetings

I have two classes and I want to use the Squeezenet network for YOLOv3 purposes. However, the last three layers in the network ('pool10', 'prob', and 'ClassificationLayer_predictions') have an ouput of 1x1x1000. How can I change the network for my purpose?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Hornett 2024-9-25

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1907940-how-to-modify-the-fully-connected-layer-for-yolo-purposes#answer_1522260

Hi Fahmi,

You can use MATLAB's removeLayers function in order to remove a layer from a neural network, then you can add your own custom layer with the given output size of 1x1x1000 using addLayers function.

Hope it helps!