can not run with local picture T.T

[oceanusXXD]

When I replace an uploaded image with a new one, it will display a new bug,I have checked that the image is in RGB format

Traceback (most recent call last): File "/home/gpu/data/Wonder3D/test_mvdiffusion_seq.py", line 333, in main(cfg) File "/home/gpu/data/Wonder3D/test_mvdiffusion_seq.py", line 269, in main validation_dataset = MVDiffusionDataset( File "/home/gpu/data/Wonder3D/mvdiffusion/data/single_image_dataset.py", line 138, in init image, alpha = self.load_image(os.path.join(self.root_dir, file), bg_color, return_type='pt') File "/home/gpu/data/Wonder3D/mvdiffusion/data/single_image_dataset.py", line 205, in load_image alpha_np = np.asarray(image_input)[:, :, 3] IndexError: index 3 is out of bounds for axis 2 with size 3 Traceback (most recent call last): File "/home/gpu/data/Wonder3D/wonder3d/bin/accelerate", line 8, in sys.exit(main()) File "/home/gpu/data/Wonder3D/wonder3d/lib/python3.10/site-packages/accelerate/commands/accelerate_cli.py", line 47, in main args.func(args) File "/home/gpu/data/Wonder3D/wonder3d/lib/python3.10/site-packages/accelerate/commands/launch.py", line 994, in launch_command simple_launcher(args) File "/home/gpu/data/Wonder3D/wonder3d/lib/python3.10/site-packages/accelerate/commands/launch.py", line 636, in simple_launcher raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) subprocess.CalledProcessError: Command '['/home/gpu/data/Wonder3D/wonder3d/bin/python3', 'test_mvdiffusion_seq.py', '--config', './configs/mvdiffusion-joint-ortho-6views.yaml']' returned non-zero exit status 1.

[xxlong0]

Hello, the test_mvdiffusion_seq.py takes RGBA image as input. You need input an image with mask. You can run local gradio app, which can support RGB and RGBA images.

[oceanusXXD]

Thank you,i got it,i try it successfully,but when i change the size of image,i need change the sample_size in configs,it is a bug?

when i set [640,960]， RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 64 but got size 80 for tensor number 1 in the list.

[xxlong0]

Hello, you don't need to modify the image size of the config file. The images with any sizes will be reshaped into (256, 256) size. Our model currently only supports 256x256.