too many indices for array

lucabergamini / VAEGAN-PYTORCH

VAEGAN from "Autoencoding beyond pixels using a learned similarity metric" implemented in Pytorch. Clean, clear and with comments.

181 stars 34 forks source link

Open yueanga opened 3 years ago

yueanga commented 3 years ago

when i ran with

python main.py --train_folder </.../...> --test_folder</.../...>

an error occured in around line 161

loss_nle_mean(torch.mean(nle_value).data.cpu( ).numpy( )[ ]) IndexError:too many indices for array: array is 0-dimensional,but 1 were indexed

how can i solve this? thank you!

liaini commented 2 years ago

loss_nle_mean(torch.mean(nle_value).data.cpu().numpy()) works~

zideliu commented 2 years ago

have you run this code succeedly? I meet "inplace operation" error,