search

TobyPDE / FRRN

Full Resolution Residual Networks for Semantic Image Segmentation
MIT License
278 stars 93 forks source link

input image is black #24

Closed manuel-88 closed 7 years ago

manuel-88 commented 7 years ago

Hey, I tested your framework with the cityscape dataset and the trained models (predict.py) but the output is very bad (losses between 100 - 500). I checked the output images(image, gt_img and pred_img) and saw that the RGB is just black. The gt is the same like from the dataset and the pred is a very bad segmented image.

The paths to the cityscape seems to be right and the dependency check runs with no error.

Thank you for help.

TobyPDE commented 7 years ago

Can you make sure that the path to the model is correct? The code does not raise an error if the model file doesn't exist.

manuel-88 commented 7 years ago

yes the model path was wrong. The segmentation works, thank you.

But why is the plotted image of the input still black?

TobyPDE commented 7 years ago

I'm not entirely sure. The image is a [0, 1] normalized floating point image. Maybe your installed version of OpenCV can't handle floating point images (I tested with OpenCV 3.x).