How to change the code in Python so that at the end not random photos in the neural network are tested, but photos from the folder?

Question

Python

This is the code from Kaggle and this part from testing This code predicts a random photo from the dataset
And I have a question how to change the code so that it does not display a random photo, but a photo from a folder
here is a link to the Kaggle project https://www.kaggle.com/paoloripamonti /derma-diseas...
And this code is the very part of neural network testing

def load_image(filename):
    img = cv2.imread(os.path.join(BASE_DATASET_FOLDER, TEST_FOLDER, filename))
    img = cv2.resize(img, (IMAGE_SIZE[0], IMAGE_SIZE[1]) )
    img = img /255
    
    return img


def predict(image):
    probabilities = model.predict(np.asarray([img]))[0]
    class_idx = np.argmax(probabilities)
    
    return {classes[class_idx]: probabilities[class_idx]}

for idx, filename in enumerate(random.sample(test_generator.filenames, 10)):
    print("SOURCE: class: %s, file: %s" % (os.path.split(filename)[0], filename))
    
    img = load_image(filename)
    prediction = predict(img)
    print("PREDICTED: class: %s, confidence: %f" % (list(prediction.keys())[0], list(prediction.values())[0]))
    plt.imshow(img)
    plt.figure(idx)    
    plt.show()

Answer 1

Where is filename from?
If you are uploading a photo to this folder, then change filename to the file name