How to displaying an image with 6 channels instead of 3

vision
#1

I had created my own dataloader to work with the CycleGan project.

I generated a new DataSet that cat 2 images together to form an input with 6 channels. This also causes the output of the network to be 6 channels.

When I tried passing the output into Visdom to display, this was the error message i got

Traceback (most recent call last):
  File "train.py", line 45, in <module>
    visualizer.display_current_results(model.get_current_visuals(), epoch, save_result)
  File "/home/stormaggedon/fyp/util/visualizer.py", line 109, in display_current_results
    padding=2, opts=dict(title=title + ' images'))
  File "/home/stormaggedon/pytorch-CycleGAN-and-pix2pix/env/lib/python3.7/site-packages/visdom/__init__.py", line 335                                                                                                                        , in wrapped_f
    return f(*args, **kwargs)
  File "/home/stormaggedon/pytorch-CycleGAN-and-pix2pix/env/lib/python3.7/site-packages/visdom/__init__.py", line 975                                                                                                                        , in images
    grid[:, h_start:h_end, w_start:w_end] = tensor[k]
ValueError: could not broadcast input array from shape (6,64,64) into shape (3,64,64)

Any suggestions on what I can do to solve this?

#2

I hope someone else can give a better answer. I had done something similar and found I needed to break it into two 3 channel images like img[:3] & img[3:] if you want, you can do something like a cv2.addWeighted to see all 6 channels in one image by combining the two 3 channel images back to one 3 channel image and showing that.