How does CE loss get computed concretely on multi-class segmentation?

1

Hello,I found someone use it like this:
celoss(logits,mask)
here
logits has shape [2, 22, 256, 256]
mask has shape [2, 256, 256]

and category type is encoded into mask,for example,if a pixel is belongs to a people,it will has value==17(human’s code in VOC dataset).

Will CELoss one-hot encode mask to generate 22 channels firstly,then pairing generated mask channels with logit channels one by one to compute cross entropy?

2

Hi,

CELoss can be implemented without having to create the one hot encoding. So to reduce memory needs, our CE function takes the label as a LongTensor that contains the index to the correct class.