Chien-Chung, Lin

icon company ADLINK Technology Inc. icon location No. 66, Huaya 1st Rd., Guishan Dist., Taoyuan City 333411, Taiwan icon location Dr. Chien-Chung, Lin is currently a R&D Lead in ADLINK. He earned his PhD in Management of Information System from Yuan Ze University, Taiwan, ROC, in 2016.

Results 6 comments of Chien-Chung, Lin

RuntimeError:CUDA out of memory.

I also met the cuda out of memory problem also, and then I change the architecture using '--trunk resnet50' without using '--snapshot checkpoints/best_cityscapes_checkpoint.pth'. Besides, I also use the parameter suggested...

RuntimeError:CUDA out of memory.

@HAOCHENYE Thanks for telling that and sure that it can not training using resnet50 or resnet101 under this current version. And have you successfully training using wideresnet on single GPU?...

RuntimeError:CUDA out of memory.

> make --syncbn=False in train.py. > Besides, I also delete some data augmention and change its image transformation because the loss is hard to converge for single GPU card based...

RuntimeError:CUDA out of memory.

> Thank you very much for your reply. Did you use Resnet50 to train from scratch instead of using the original pre-training checkpoint? So how do I modify the code...

I can't find the dataset for this code, could anyone share it with me?

Dear hxtisme, please refer to this: #37 Simply register then download it.

subprocess.CalledProcessError: Command '['ninja', '-v']'

Dear all, I'm using python3.6 and also met this problem. I fixed this problem by modify the /usr/local/lib/python3.6/site-packages/torch/utils/cpp_extension.py from ['ninja', '-v'] to ['ninja', '--version']. Hope this information could help you...