Training a model using UNET and ResNet34 to do image segmentation on street images. Image Segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as image objects).
You can find more about the dataset here.
If you are having trouble opening the notebook with github click here to view it with NBViewer.
We can see that the predictions in this case were pretty accurate. It predicted the buildings, the trees, the vegetation, Bicyclist, Car(Auto), Road, Sign Symbol, Pole, fence. I don't think I have any complains with it.