Krdytkyu

I have a grayscale image that has only 1 channel. I am using a code that expects all images to have three channels. How can I convert my image to a 3 channel image using some Linux commands?

Here is the error I get and I do not want to change the code, rather I want to change the image:

Traceback (most recent call last):

  File "get_img_vec.py", line 22, in <module>

    nd_arr = img2vec.get_vec(img)

  File "../img_to_vec.py", line 43, in get_vec

    h_x = self.model(image)

  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__

    result = self.forward(*input, **kwargs)

  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torchvision-0.2.1-py3.6.egg/torchvision/models/resnet.py", line 139, in forward

  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__

    result = self.forward(*input, **kwargs)

  File "/scratch/sjn-p3/anaconda/anaconda3/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 301, in forward

    self.padding, self.dilation, self.groups)

RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[1, 1, 224, 224] to have 3 channels, but got 1 channels instead

The image:

$ identify 10524.jpg

0524.jpg JPEG 1050x550 1050x550+0+0 8-bit PseudoClass 256c 80.7KB 0.000u 0:00.000

This is the image:

1. 
   

   Install ImageMagick if needed:

   
   
   

   sudo apt install imagemagick
   
   

   
   

(You can also install the latest release from source on Ubuntu 18.04 following this guide)

2. 
   

   To separate image channels run:

   
   
   

     convert rose: -channel R -separate separate_red.gif
   
     convert rose: -channel G -separate separate_green.gif
   
     convert rose: -channel B -separate separate_blue.gif
   
   

   
   
   

   (following this guide)

   
   
   

   or to combine RGB image channels run:

   
   
   

   convert  separate_red.gif separate_green.gif separate_blue.gif 
   
            -combine -set colorspace sRGB rose_combined.gif
   
   

   
   
   

   (following this guide)

   
   

This will work for JPG too. Also you can try combining copies of the same gray-scale images with 3 different channels.

The following Python code works:

import cv2

import numpy as np

img = cv2.imread('10524.jpg')

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

img2 = np.zeros_like(img)

img2[:,:,0] = gray

img2[:,:,1] = gray

img2[:,:,2] = gray

cv2.imwrite('10524.jpg', img2)