MedSegDiff
MedSegDiff copied to clipboard
use DDIM error
Bot detected the issue body's language is not English, translate it automatically. ๐ฏ๐ญ๐ป๐งโ๐คโ๐ง๐ซ๐ง๐ฟโ๐คโ๐ง๐ป๐ฉ๐พโ๐คโ๐จ๐ฟ๐ฌ๐ฟ
Title: use NO error
segmentation_sample.py๏ผI want to use DDIM to speed up, added the following code, but it reports an error, hope to get an answer โ--use_ddim True --timestep_respacing ddim250โ
RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
File "/home/david/anaconda3/envs/py37tor181/lib/python3.7/site-packages/torch/cuda/streams.py", line 79, in record_event
event.record(self)
File "/home/david/anaconda3/envs/py37tor181/lib/python3.7/site-packages/torch/cuda/streams.py", line 154, in record
super(Event, self).record(stream)
RuntimeError: CUDA error: device-side assert triggered
Do you solve this question? I have same problem.
I guess the author does not use DDIM before.
ย ย ๆจๅฅฝ๏ผๆจ็้ฎไปถๆๅทฒๆถๅฐ๏ผๆไผๅฐฝๅฟซๅๅค็๏ผ่ฐข่ฐข๏ผ
Bot detected the issue body's language is not English, translate it automatically. ๐ฏ๐ญ๐ป๐งโ๐คโ๐ง๐ซ๐ง๐ฟโ๐คโ๐ง๐ป๐ฉ๐พโ๐คโ๐จ๐ฟ๐ฌ๐ฟ
โ โ Hello, I have received your email and I will reply as soon as possible, thank you!