Help with inference needed.

[roshan2024nar]

Hello is there any code or way i can infer for single image only i have shadow free image and object mask

[nononononno]

Replace --shadowfree_imgs_path and --object_masks_path with your data paths, then run infer_single.py.

[roshan2024nar]

Thanks man!!!!!!!!!!!!!!!!!!

There is one issue i can't find below in my whole codebase

from libcom_dataset import TestDataset, TestDatasetBatch
from train_post_process_predictor import PostProcess

[nononononno]

We have updated tutorial_dataset.py and infer_single.py. You can try again.

[roshan2024nar]

I only have one issue I'm running for a single image

Loaded state_dict from [./models/pretrained_models/Shadow_cldm.ckpt]
Data shape for DDIM sampling is (5, 4, 64, 64), eta 0.0
Running DDIM Sampling with 50 timesteps
DDIM Sampler: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [08:55<00:00, 10.71s/it]
Data shape for DDIM sampling is (5, 4, 64, 64), eta 0.0
Running DDIM Sampling with 50 timesteps

the model is running successfully but it just keeps going on and at the end i get error

Traceback (most recent call last):
File "infer_single.py", line 102, in
shadowfree_img = cv2.resize(shadowfree_img, (width, height))
cv2.error: OpenCV(4.4.0) C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-k8sx3e60\opencv\modules\imgproc\src\resize.cpp:3929: error: (-215:Assertion failed) !ssize.empty() in function 'cv::resize'

also i was getting error for "ZT" which was not being passed