Semantic segmentation with greyscale images

Question

Semantic segmentation with greyscale images

VansFannel

2022年2月24日 04:05

I'm trying to reproduce a research with greyscale images instead of colour images.

I have found that there are pre-trained networks, like VGG16, with ImageNet. But that dataset has colour images, and I can't use it because I'm going to use greyscale images.

Is there any pre-trained network with greyscale images?

Failing that, I can also train a network with a greyscale image dataset but I can't find any.

Topic pretraining vgg16 cnn dataset

Category Data Science

Paul · Accepted Answer · 2021年5月22日 08:37

1

Paul answered at 2021年5月22日 08:37

Your problem is that your dataset has one value per pixel, whereas ImageNet expects 3? Just convert your data to "color images" by passing the same value on all 3 (RGB) channels.

score 1 · Accepted Answer · 2020年9月15日 20:26

1

answered at 2020年9月15日 20:26

Use ImageNet, convert every image to grayscale and train VGG16.

Semantic segmentation with greyscale images

About