faster r-cnn test all images in folder

Question

I have trained my model using faster-rcnn on my computer. As you know , using script you can only test 1 image. But I want to test all images in my test folder. I have to write a code (using loops) which enables me to do that. Is there anyone can help me about this problem. Thanks in advance. Sincerely.

Answer 1

Hello, Here you can find a function that I implemented for testing Faster R-CNN on a set of images:

def get_folder_results(detector, image_dir, device):
       ' The detector represents your Faster R-CNN model,
         image_dir represents the folderpath containing the images,
         device : the device used to train (CPU, GPU ...) '
 for image in os.listdir(image_dir):
    image_path = os.path.join(image_dir, image)
    input_images = [T.ToTensor()(Image.open(image_path)).to(device)]
    prediction = detector(images)
    print(prediction)

    

After executing this function you will get a prediction per image where each prediction represents the coordinates of the bounding boxes and the corresponding class).