ground truth predicted

predictgroundtruth.py

# Make preds on a series of random images
import os
import random

plt.figure(figsize=(20, 14))
for i in range(3):
  # Choose a random image from a random class 
    class_name = random.choice(class_names)
    filename = random.choice(os.listdir(test_dir + "/" + class_name))
    filepath = test_dir + class_name + "/" + filename

    # Load the image and make predictions
    img = load_and_prep_images(filepath, scale=False) # don't scale images for EfficientNet predictions
    pred_prob = model_3.predict(tf.expand_dims(img, axis=0)) # model accepts tensors of shape [None, 224, 224, 3]
    pred_class = class_names[pred_prob.argmax()] # find the predicted class 

    # Plot the image(s)
    plt.subplot(1, 3, i+1)
    plt.imshow(img/255.)
    if class_name == pred_class: # Change the color of text based on whether prediction is right or wrong
        title_color = "g"
    else:
        title_color = "r"
    plt.title(f"actual: {class_name}, pred: {pred_class}, prob: {pred_prob.max():.2f}", c=title_color)
    plt.axis(False);