110. Preprocessing Images

When testing out your model’s output for computer vision tasks, you’ll need to apply the same preprocessing methods you’ve applied during training, to the images you want to test out. Here is one way to implement.

1. Import Images

   from PIL import Image
   input_img = Image.open("PATH_TO_IMAGE.jpg")
   

2. Define preprocessing method same as the method used during training

   import torchvision
   input_preprocess = torchvision.transforms.Compose([
                           torchvision.transforms.Resize((512,512)), #Resize Image to 512x512
                           torchvision.transforms.ToTensor()]) # change values from 0~255 to 0~1
   

3. Apply preprocessing method

   processed_input_img = input_preprocess(input_img)