您正在关注此问题

您将在关注的内容源中看到更新。
您可能会收到电子邮件，具体取决于您的通信预设项。

Transfer learning on a very small dataset

3 次查看（过去 30 天）

显示更早的评论

Nbillah 2019-1-17

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset

⋮

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset

评论： Nbillah 2019-4-15

Hi, I have total 20 images from two datasets i.e. Train and Test.

I want to perform a pilot study on transfer learning using Alexnet architecture. Is this going to hurt me? Can I not perform this transfer learning on such a very small dataset?

9 个评论
显示 7更早的评论隐藏 7更早的评论

Kevin Chng 2019-1-17

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661356

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661356

It's subjective. Generally, we believe larger dataset would provide more information to your network to get higher accuracy. However, why don't you try out with your current dataset first? Subsequently, you may justify the performance, and think how to improve the accuracy.

https://www.mathworks.com/help/deeplearning/examples/transfer-learning-using-alexnet.html

Nbillah 2019-1-18

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661942

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661942

Thank you so much, and I checked with my dataset and its very low accuracy i.e 66.67%.

Image Analyst 2019-1-18

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661943

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661943

Then I guess you have your answer. Can you post your script? Maybe there's something that can be done. What is in the images that you want to find? Can you post 1 or 2 training images with the things identified?

Nbillah 2019-1-19

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661962

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661962

编辑：Nbillah 2019-1-20

Thank you. I have total 20 images, 10 each group for Normal and Glaucoma. I did ROI extraction from real images and then tried on transfer learing example.

Would you please tell me what should be the maxepoch and minibatchsize for my data?

Image Analyst 2019-1-19

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661991

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_661991

It seems that deep learning is not needed. Simply find the area. Glaucoma has small area while normal has large area. Would you consider abandoning Deep Learning to do a much simpler traditional method using regionprops() to find the area of the blobs in your binary image?

Or do you just want to use deep learning as a learning exercise even though it's probably not the best approach?

Nbillah 2019-1-20

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_662153

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_662153

Thank you for your comment. Yes I did the calculation for area. Actually I want to train a machine with the shape and size of this extract ROI.

Nbillah 2019-4-1

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_688395

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_688395

Hi, I used Alexnet pretrained CNN to train my images . I got the following graph, I used 120 binary images per two group. And I got the following result. Please have a look the following graph and comment about the result. The graph is good or is it overfit/underfit? Can I go further with this CNN to train same segmented images with increasing my data size?

Shounak Mitra 2019-4-12

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_693030

⋮

链接

此评论的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/440142-transfer-learning-on-a-very-small-dataset#comment_693030

Nahida,

The training progress chart looks 'just right'. Is the 80% accuracy acceptable in your case? Sometimes even 99% is bad and other times even 70% is good! You can go ahead with more data. I don't see any problem. Good luck.

Shounak

Nbillah 2019-4-15