search

JuliaWolleb / Diffusion-based-Segmentation

This is the official Pytorch implementation of the paper "Diffusion Models for Implicit Image Segmentation Ensembles".
MIT License
272 stars 35 forks source link

Have you ever encountered this problem when running segmentation_sample.py? #12

Closed jaceqin closed 1 year ago

jaceqin commented 1 year ago

sampling step 0 sampling step 900 sampling step 800 sampling step 700 sampling step 600 sampling step 500 sampling step 400 sampling step 300 sampling step 200 sampling step 100 sampling step 0 sampling step 900 sampling step 800 sampling step 700 sampling step 600 sampling step 500 sampling step 400 sampling step 300 sampling step 200 sampling step 100 sampling step 0 Traceback (most recent call last): File "segmentation_sample.py", line 127, in main() File "segmentation_sample.py", line 71, in main b, path = next(data) #should return an image from the dataloader "data" File "/home/x012/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/home/x012/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 560, in _next_data index = self._next_index() # may raise StopIteration File "/home/x012/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 512, in _next_index return next(self._sampler_iter) # may raise StopIteration StopIteration

JuliaWolleb commented 1 year ago

Is it possible that you iterated through your whole test dataset? I just realized that the line while len(all_images) * args.batch_size < args.num_samples: is always true, so your algorithm stops once all images of your dataloader are through

jaceqin commented 1 year ago

Hello, can you share codes for generating uncertainty map and code for the scores [ Dice,HD95, Jaccard Index ] you used? 从 Windows 版邮件https://go.microsoft.com/fwlink/?LinkId=550986发送

发件人: @.> 发送时间: 2022年11月2日 15:25 收件人: @.> 抄送: @.>; @.> 主题: Re: [JuliaWolleb/Diffusion-based-Segmentation] Have you ever encountered this problem when running segmentation_sample.py? (Issue #12)

Is it possible that you iterated through your whole test dataset? I just realized that the line while len(all_images) * args.batch_size < args.num_samples: is always true, so your algorithm stops once all images of your dataloader are through

― Reply to this email directly, view it on GitHubhttps://github.com/JuliaWolleb/Diffusion-based-Segmentation/issues/12#issuecomment-1299688510, or unsubscribehttps://github.com/notifications/unsubscribe-auth/AZYM7YTBUH6ZHZ6Z6ONDZKLWGIJMXANCNFSM6AAAAAARUXZOKM. You are receiving this because you authored the thread.Message ID: @.***>

saisusmitha commented 1 year ago

@jaceqin if you have figured out the solution to your question kindly share that code for generating the scores and maps. It would be really helpful.