Skip to content

issues Search Results · repo:SuperMedIntel/MedSegDiff language:Python

Filter by

200 results
 (63 ms)

200 results

inSuperMedIntel/MedSegDiff (press backspace or delete to remove)

SuperMedIntel/MedSegDiff
How is the segmentation mask given to the model for multi label segmentation mask

If the segmentation mask has just two class background and cancer we can give it as mask with 1 and 0s If there are multiple classes, how are they given, we can t do diffusion directly on the segmentation ...
  • nobleaustine
  • 2
  • Opened 
    7 hours ago
  • #214

SuperMedIntel/MedSegDiff
Why are UNetModel_v1preview and UNetModel_newpreview the same in this code?

  • Liu-XL-code
  • Opened 
    2 days ago
  • #213

SuperMedIntel/MedSegDiff
About BraTS sample result

Thanks to this effort, I tried to reproduce the BRATS2021 dataset, and I modified the saved file to NII format. I wondered why the final sample result was an MRI image without a mask, how do I get the ...
  • springbreeze7111
  • 5
  • Opened 
    17 days ago
  • #212

SuperMedIntel/MedSegDiff
Why are DP and DDP used together?

Excuse me, I don t understand the multi-GPU training model using DP in segmentation_train.py and then using DDP in train_util.py. Is there a conflict?
  • ailinxiqingcheng
  • Opened 
    on Jan 9
  • #211

SuperMedIntel/MedSegDiff
对于模型v1,使用的损失函数是loss = (losses["loss"] * weights + losses['loss_cal'] * 10).mean()？以及在segmentation_sample.py文件中，debug时，输出的第一张图片(ss)是怎么的来的，以及使用的是前面的损失函数吗？ 输出的最后一张图片(c)是怎么的来的 是使用loss_cal的损失函数计算得来的吗？ 希望有人能解答一下

  • LiuYM00
  • 1
  • Opened 
    on Dec 16, 2024
  • #209

SuperMedIntel/MedSegDiff
对于ISIC2016数据集 ,60000 epoch， 大概需要训练到多少步 使用的batch_size是2

  • LiuYM00
  • 1
  • Opened 
    on Dec 5, 2024
  • #208

SuperMedIntel/MedSegDiff
btcvloader

Thank you for all your contributions! But I have some questions: 1. When I read the code, I found that the script(btcvloader.py) is empty. Can you provide it(multi-organ segmentation)? 2. How to modify ...
  • dulicui742
  • 1
  • Opened 
    on Dec 5, 2024
  • #207

SuperMedIntel/MedSegDiff
How to use dim

how to use ddim if I should set time step
  • Hxxxz0
  • Opened 
    on Dec 4, 2024
  • #206

SuperMedIntel/MedSegDiff
sample得到预测的噪声后怎么去除噪声呢？

我的任务是实现分割，输入的图片对是原图 分割mask图，在使用readme的教程中训练的我的代码，结果发现 模型参数ModelMeanType.EPSILON: noise,也就是unet预测的noise么，调用segmentation_sample.py函数得到的 sample, x_noisy, org, cal, cal_out = sample_fn( model, (batch_size, ...
  • qxxfd
  • 2
  • Opened 
    on Dec 1, 2024
  • #205

SuperMedIntel/MedSegDiff
为什么训练出现了完全噪声的结果，如图所示的原图和标签的训练对，20000+图片对（单通道灰度图）训练200epoch得到如图结果，sample_step=30,是否有朋友知道是什么原因呢

image
  • qxxfd
  • 1
  • Opened 
    on Nov 30, 2024
  • #204
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub