Closed ghost closed 2 years ago
Hi, since the feature extractor is pretrained on the RGB dataset ImageNet, you will have to convert your image into RGB. For converted grayscale images helpful features should still be found from my experience. Otherwise you would have to use a feature extractor that has been pretrained on your type of image.
Best regards Marco
Hi, Thank you very much for your work. Can it be possible for this code to process only one channel of images?