does is affect NN training accuracy if the color format of images is BGR not RGB?

Question

I'm training Neural Network with ImageNet dataset and I noticed that images are in BGR color format when I read them using OpenCV function cv2.imread(), so does is affect training accuracy?, if yes then how can I change it to RGB in pytorch?

Answer 1

It will not affect your NN's accuracy, in general. However, if you are using a pre-trained CNN, then it likely expects RGB images as input, and will not do as well on BGR images initially and will have to re-learn its weights for BGR.

You can convert BGR to RGB using cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB).

You can also consider the following alternatives for reading images:

• torchvision.io.read_image(path) (https://pytorch.org/vision/stable/io.html#image)
• torch.from_numpy(np.array(PIL.Image.open(path)))
• torchvision.transforms.functional.pil_to_tensor(PIL.Image.open(path)) (https://pytorch.org/vision/stable/transforms.html#torchvision.transforms.functional.pil_to_tensor)