jakeret / tf_unet

Generic U-Net Tensorflow implementation for image segmentation
GNU General Public License v3.0
1.9k stars 748 forks source link

How to get output of a batch of input files #249

Open I-CANT-CODE opened 5 years ago

I-CANT-CODE commented 5 years ago

Hello,

I am simplifying my question

I have images in a folder that I want to use my trained model on to segment. I am really confused on how to do this and have it output images. I would greatly appreciate any help.

jakeret commented 5 years ago

You can load your data using the same data provider mechanism - so you ensure that the same pre-processing steps are being applied

I-CANT-CODE commented 5 years ago

ok, well once I load them and then use net.predict(), how can I then safely convert the batch of tensors to rob images and save them to image files? I tried doing this with my own code and got all black or all white images.