advimman / lama

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Home Page:https://advimman.github.io/lama-project/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

predict, ValueError:not enough values to unpack (expected 2, got 1)

leayz-888 opened this issue · comments

First of all, thank you for your great work!
I want to use a lama-fourier model trained on the places dataset to make predictions on my own dataset, the command I use is:
python ./bin/predict.py model.path=/home/project/lama/lama-regular/ indir=/home/project/lama/my_dataset/eval/random_medium_512/ outdir=/home/project/lama/inference/my_dataset /random_medium_512, I set refine to True, but got an error:
File "./bin/predict.py", line 75, in main
cur_res = refine_predict(batch, model, **predict_config.refiner)
File "/home/project/lama/saicinpainting/evaluation/refinement.py", line 308, in refine_predict
image_inpainted = _infer(image, mask, forward_front, forward_rears, image_inpainted, orig_shape, devices, ids, n_iters, lr)
File "/home/project/lama/saicinpainting/evaluation/refinement.py", line 128, in _infer
z1,z2 = forward_front(masked_image)
ValueError: not enough values to unpack (expected 2, got 1)
But when I set refine to False, this problem disappears. How can I solve this problem? Greatful!

Hey thanks for raising the issue. I'm looking into it, will release a fix soon!