UTNet

UTNet copied to clipboard

Hello, thanks for providing this repo to your really nice work :) I am wondering if there is any way of getting some final checkpoints of some already trained checkpoints....

TaWald

您好！最近我也在做心脏分割项目的研究，看了您的工作，对我的研究帮助非常大，先提前感谢您。在复现您的代码的时候，碰到了一些疑问，想来请教一下您。 1：您在MM数据集上，训练集150例病人，测试集170例病人（剩余三十例病人医院不公开）。看到您是直接拿测试集当作验证集，取得在Vendor A 上的最优的效果，是这样子吗？ 2：我完全按照您的方法对数据集做预处理，按照您的默认设置训练，得到的结果如下： AVG_dice_list : [0.89811725 0.82059008 0.86868217] AVG_ASD_list : [0.93223253 0.79887591 1.10695938] AVG_HD_list : [0.93223253 0.79887591 1.10695938] 请问您的HD和ASD计算方法是按照您的代码里那样子运行吗？为什么值这么小，而且 ASD=HD。

zeng-su123

Hi All, Please be noted when I use the above mentioned arguments I get list index out of range error due to the following line num_blocks[-3] although list length is...

Yussef93

In your paper, the number of the testing dataset is 200. However, the sum of patient ids in Testing_A.csv, Testing_B.csv, Testing_C.csv, and Testing_D.csv is 170. So where are the rest...

buaaduke