I want to use a pre trained Resnet 50 as a backbone for Unet model. But the issue is resnet 50 is expecting the size of image as 197 x 197 3D channel but the image of mine is 128 X 128 x 1D channel. Is there any keras or tensorflow implementation on those.

  • $\begingroup$ You can always resize the image and repeat them 3 times over the third axis $\endgroup$ – Djib2011 Sep 14 '18 at 23:35

When you import ResNet50 import in this way:

image_input=Input(shape=(512, 512, 3))
model = ResNet50(input_tensor=image_input, include_top=False)

After that, you can work with your desired image_size


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.