I am working on pascal voc dataset 2012 challenge for semantic segmentation problem. This problem consists of 21 classes. Each pixel is class index labeled as background=0,classes from 1-20 index values, and 255 index value for void class. For more information on all of these classes: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/segexamples/index.html
I was working on this dataset using pytorch using fully convolutional networks: https://arxiv.org/abs/1411.4038
I used ‘’‘torch.nn.CrossEntropyLoss()’’’ as my loss function. In this loss function we have an attribute called as ignore_index. This attribute was allowing me to ignore the index value 255 present in the image. My problem is how can I ignore this 255 pixel value in fastai ?
You can use that loss function and param in fastai.
Hi, i am trying to train my model with pascal voc2012 segmentation and i couldn’t find a way to implement the classes, can you show me an example of doing that? How did you feed the classes to the model?
Or something like how you defined your databunch?
I am struggling with this for a while and i really need your help, thanks so much!