search

sagieppel / Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation

68 stars 40 forks source link

Doesn't predict correctly #11

Open Djeane89 opened 5 years ago

Djeane89 commented 5 years ago

Hi,

Thank you so much for sharing your code. I have tried it.

The training and validation are run successfully. However, after run the Inference.py, the prediction result "/label" only shown black intensity in .png prediction image.

Please let me know where can be the problem?

Thanks

sagieppel commented 5 years ago

Is the value of the pixels is all zeros or is it just look black. The png image translates labels into 0-256 intensity values so if you have to say 5 labels the max intensity is 4 and the annotation mask will look dark even if the prediction was done correctly.

Djeane89 commented 5 years ago

looks like the value of the pixels is all zeros.

if it looks dark even if the prediction was done correctly, how can I check it?

sagieppel commented 5 years ago

im=cv2.imread("Prdicintion.png") # read predicted label map (if its not already loaded) print(im.max()) # print max value of label map

Djeane89 commented 5 years ago

I have checked it. The output is '0'