-
Notifications
You must be signed in to change notification settings - Fork 62
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
LexerNoViableAltException: 2020 & import ddpm error #3
Comments
I fix the problem, the terminal misunderstand the path |
hi, the problem still exist. I cloned the recent code and yet saying no ddpm. |
thanks you for sharing your experience.Could you share your data directory.I would be very thankful. |
我把数据放到了和克隆的代码“medicaldiffusion”这个文件夹同一级的目录下, 目录就像我用的参数一样,只是BraTS 2020没法在终端里使用,因为空格会被识别成分隔下一个参数,所以把空格替换成了下划线 |
I failed to run the code, either. Maybe you can try the command |
thank you very much for your reply. |
@ytwas 您好,请问您复现了这个代码了么?我在实现这个代码加载数据集的时候,每次都会报错,说数据集不可用。可以确定的是我的数据集名字是没有空格的。 |
I have experienced the same problem. Can you help me? |
thanks for sharing this awesome work! But I cannot run the code, due to some errors.
when I use the provided command to train vqgan:
PL_TORCH_DISTRIBUTED_BACKEND=gloo python train/train_vqgan.py dataset=brats dataset.root_dir=../data/BraTS/BraTS 2020 model=vq_gan_3d model.gpus=1 model.default_root_dir_postfix='flair' model.precision=16 model.embedding_dim=8 model.n_hiddens=16 model.num_workers=32 model.gradient_clip_val=1.0 model.lr=3e-4 model.discriminator_iter_start=10000 model.perceptual_weight=4 model.image_gan_weight=1 model.video_gan_weight=1 model.gan_feat_weight=4 model.batch_size=2 model.n_codes=16384 model.accumulate_grad_batches=1
The error information:
Then I try to use
export PYTHONPATH=$PYTHONPATH:~/gitcode/medicaldiffusion/ddpm
to fix it,but a new error come up:
Thanks in advance!
The text was updated successfully, but these errors were encountered: