search

vt-vl-lab / 3d-photo-inpainting

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
https://shihmengli.github.io/3D-Photo-Inpainting/
Other
6.9k stars 1.11k forks source link

对照片尺寸大小有要求吗，我传了一张图片分辨率是249x324执行失败 #119

Open handongzhe opened 3 years ago

handongzhe commented 3 years ago

输出信息如下： running on device 0 0% 0/1 [00:00<?, ?it/s]Current Source ==> car2 Running depth extraction at 1611731040.6164544 initialize device: cpu start processing processing image/car2.jpg (1/1) torch.Size([1, 3, 384, 320]) finished 0% 0/1 [00:02<?, ?it/s] Traceback (most recent call last): File "main.py", line 72, in vis_photos, vis_depths = sparse_bilateral_filtering(depth.copy(), image.copy(), config, num_iter=config['sparse_iter'], spdb=False) File "/content/3d-photo-inpainting/bilateral_filtering.py", line 31, in sparse_bilateral_filtering vis_image[u_over > 0] = np.array([0, 0, 0]) ValueError: shape mismatch: value array of shape (3,) could not be broadcast to indexing result of shape (4003,249)

yfszzx commented 1 year ago

I know how to repair https://github.com/vt-vl-lab/3d-photo-inpainting/issues/176