unet-nested-multiple-classification icon indicating copy to clipboard operation
unet-nested-multiple-classification copied to clipboard

This repository contains code for a multiple classification image segmentation model based on UNet and UNet++

Results 10 unet-nested-multiple-classification issues
Sort by recently updated
recently updated
newest added

inference的结果里能不能加上map能指标

请问这个代码训练的时候不需要添加预训练模型么?

运行时报这种错,是需要训练集中各个图像的size必须一致吗?

你好,用你的代码和你的数据复现,损失韩式很大,验证集才60几,是否有问题?

When I training the UNet with original settings and dataset , nothing is classified, as is shown in the image ![image](https://user-images.githubusercontent.com/48800355/113842420-3b0d2200-97c5-11eb-8caa-2ec714cc8530.png)

for masks, I make a multi-classification for 10 classes, I set the value of background as "0" for gray image, but in the testing result, I can always see the...

INFO: Using device cuda INFO: Network: NestedUNet model 3 input channels 3 output channels (classes) Bilinear upscaling INFO: Creating dataset with 20 examples training stops after this. can anyone help

老哥,能给下数据处理那块的代码吗,将json转成图片,再获取全局类别,将图片转成uint8的格式