아파서 내일 할 것만 정리
새벽부터 메스껍고 구토할 거 같아서 병원에서 약타고 오후 반차...
오늘 unet 을 써서 학습하려고 했는데 일단 찾아놓은 것만 올려놓고 ㅌㅌ한다
unet 코드
https://github.com/milesial/Pytorch-UNet
milesial/Pytorch-UNet
PyTorch implementation of the U-Net for image semantic segmentation with high quality images - milesial/Pytorch-UNet
github.com
여기서는 dice loss를 쓴다고 했는데 뭔 주사위 loss인가 싶어서 좀 찾아서 읽다가 눈에 초점을 잃어버림
다양한 loss에 대한 정리
https://lars76.github.io/neural-networks/object-detection/losses-for-segmentation/
Losses for Image Segmentation
In this post, I will implement some of the most common losses for image segmentation in Keras/TensorFlow. I will only consider the case of two classes (i.e. binary). If you know any other losses, let me know and I will add them.
lars76.github.io
pytorch dice coefficient loss 코드
https://gist.github.com/weiliu620/52d140b22685cf9552da4899e2160183
Dice coefficient loss function in PyTorch
Dice coefficient loss function in PyTorch. GitHub Gist: instantly share code, notes, and snippets.
gist.github.com
이제 도망칠 준비
