Tensorflow-SegNet icon indicating copy to clipboard operation
Tensorflow-SegNet copied to clipboard

Output_Image

Open tom-bu opened this issue 8 years ago • 2 comments

Is there currently a way to see all of the segmented test images? By default only one of these images is saved, which is the testing_image.png. And in model.py, I saw that there's the option of uncommenting

writeImage(im[0], 'out_image/'+str(image_filenames[count]).split('/')[-1])
count+=1

but is that enough to save more of the test images?

tom-bu avatar Jan 16 '18 06:01 tom-bu

It seemed more complicated than I thought at first, but I got it. However, if anyone is still wondering how to see all of the segmented images, I'll go ahead and answer my question. You have to go to model.py, and first uncomment the two line from my previous post. Then, write

count=0

under

with tf.Session() as sess:

and add a file named "out_image" in your Tensorflow-SegNet file. The images should all be stored there. And that's it.

tom-bu avatar Jan 16 '18 10:01 tom-bu

However, it would be nice if the master file already had the count=0 commented in model.py and have an out_image file to make it more convenient to get right away.

tom-bu avatar Jan 16 '18 10:01 tom-bu