-2

i'm doing some research about predict soundwave speed using thousand of pictures of rocks. each picture of rock layer is taged with a vlaue of soundwave speed. i'm trying to use tensorflow to train this datasets. but it's not a problem of classification, it's more like a problem of regression analysis except training dataset is image not some numberic data. i'm a beginner of tensorflow. please someone teach me how to solve this problem.

xiaoliang
  • 1
  • 3
  • Well, it is a regression task, what is your specific problem with that ? – Khoyo Jun 12 '19 at 00:52
  • thanks for your reply. i'm new to tensorflow, could you please tell me how to do this step by step ,or is there any pages or sample codes i can refer to about this kind of work? – xiaoliang Jun 12 '19 at 01:32
  • Possible duplicate of [CNN Image Recognition with Regression Output on Tensorflow](https://stackoverflow.com/questions/45528285/cnn-image-recognition-with-regression-output-on-tensorflow) – Khoyo Jun 12 '19 at 02:20

1 Answers1

1

If you're looking for a step-by-step guide on how to obtain a regressed continuous output from an image-based input using tensorflow, take a look at this guide:

https://www.pyimagesearch.com/2019/01/28/keras-regression-and-cnns/

Cheers!

Om A.
  • 140
  • 6