sagieppel

You can download the code with pretrained model from: https://zenodo.org/record/3697767 or https://drive.google.com/file/d/1wWGPoa7aKBlvml6Awe4AzJUbNlR72K6X/view

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...

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

Yes, but this specific model is old, I would recommend you have a look at this instead: [https://towardsdatascience.com/train-neural-net-for-semantic-segmentation-with-pytorch-in-50-lines-of-code-830c71a6544f](https://towardsdatascience.com/train-neural-net-for-semantic-segmentation-with-pytorch-in-50-lines-of-code-830c71a6544f )

What the error? On Thu, Mar 24, 2022, 18:26 Kitae Kim ***@***.***> wrote: > Can you double check with your train and network code? It keeps causing > errors >...

The label map you read seem to have depth of 3 while it should have no depth (one label per pixel). Checkout the which of the 3 channel of the...

The Label matrix should contain one label per pixel (one int number per pixel) as ground truth for training. It seems from the error message that the label you read...

Label file is just an image in the size of the input image but with one channel (kind of greyscale). The value of each pixel in the label image is...

Try labelme: https://github.com/wkentaro/labelme

Only checked this on cases where there are many different objects in the image, in that case, it will be impossible for a simple classification net to know which object...