How we do transfer learning using pretrained models with grey scale images as input

30 ビュー (過去 30 日間)
if we planned to do a training using greyscale images with pretrained model. It will show error. Is there is any method to train these type of images. That means apart from RGB images, how we do the transfer learning

採用された回答

Abhishek Singh
Abhishek Singh 2019 年 3 月 8 日
There might be many ways to go about it:
1. Copy and stack the image matrix three times to replicate the 3 channels of RGB
2. Stack two zero or identity matrices on top of the grey image matrix such that the Red channel has all the data and the other two channels are just place holders (not advisable)
3. Remove the other channel weights in the pre-trained model itself (very cumbersome)
This is an open-ended problem with many other creative solutions like using DeOldify GAN to color them first or just interpolating the other two channels in some way. The way to find the best solution would be to experiment with your data and pre-trained architecture

その他の回答 (0 件)

カテゴリ

Find more on Deep Learning Toolbox in Help Center and File Exchange

製品


リリース

R2018b

Community Treasure Hunt

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

Start Hunting!

Translated by