Closed marcodelmoral closed 3 years ago
Sorry, the question is too general to be answered.
Would this example help you? https://github.com/yingkaisha/keras-unet-collection/blob/main/examples/human-seg_atten-unet-backbone_coco.ipynb
My understanding is that if your pixel labels are something like 0/1/2 you may use _keras.losses.sparse_categoricalcrossentropy. For _keras.losses.categoricalcrossentropy, the labels should be in one-hot format.
My understanding is that if your pixel labels are something like 0/1/2 you may use _keras.losses.sparse_categoricalcrossentropy. For _keras.losses.categoricalcrossentropy, the labels should be in one-hot format.
Ok I understand, I was used to work with implementations that use (h,w,c) where c = number of classes. For this implementation a (h,w) mask with integer labeled pixels as classes. Thank you very much!
Great to see the progress. Closing.
Hello, I'm wondering how to do multiclass classification with Unet. I saw that a previous hot encode step is needed. My dataset consists in two classes + background. Thanks in advance!