CODEWITHSUNDEEP
conv-neural-networkgrayscaleimagenetpre-trained-model
MathMits
MathMits

Reputation: 91

VGG16 trained on grayscale imagenet

I have found the VGG16 network pre-trained on the (color) imagenet database (as .npy). Is there a VGG16 network pre-trained on a gray-scale version of the imagenet database available?

(The usual 'tricks' for using the 3-channel filters of the conv1.1 layer on the gray 1-channel input are not enough for me. I am looking at incremental improvements of the network performance, so I need to see how the transfer learning behaves when the pre-trained model was 'looking' at gray-scale input).

Thanks!

Upvotes: 7

Views: 8286

Answers (2)

ma710u5
ma710u5

Reputation: 21

@GrimSqueaker gave you the code of this paper : https://openaccess.thecvf.com/content_eccv_2018_workshops/w33/html/Xie_Pre-training_on_Grayscale_ImageNet_Improves_Medical_Image_Classification_ECCVW_2018_paper.html

However, the model trained in it is Inception v3 not VGG16.

You have two options:

  1. Use a colored pre-trained VGG16 model and duplicate one channel to the three channels
  2. Train your VGG16 model on the ImageNet grayscaled dataset.

You may find this link useful: https://github.com/zzangho/VGG16_grayscale

Upvotes: 1

GrimSqueaker
GrimSqueaker

Reputation: 422

Yes, there's this one: https://github.com/DaveRichmond-/grayscale-imagenet

Greyscale imagenet trained model, and also a version of it that's finetuned on X-rays. They showed that Imagenet performance barely drops btw.

Upvotes: 2

Related Questions