Create unit test for passing results about carnd-semantic-segmentation HOT 1 CLOSED

### In main.py at the end of run() ###
# TODO: Test that at least 80% of the road is correctly labelled and no more than 20% of non-road pixels is labelled as road
tests.test_for_training_accuracy(sess, logits, image_input, os.path.join(data_dir, 'data_road/training'), image_shape, keep_prob)

### In project_tests.py ###
## Add below imports ##
import re
import statistics
import scipy.misc
from sklearn.metrics import confusion_matrix

## Add this as final test ##
@test_safe
def test_for_training_accuracy(sess, logits, image_pl, data_dir, image_shape, keep_prob):
    print("Checking that training accuracy meets minimum requirements.")
    print("Passing this test does not necessarily mean submission is passing,\n", 
          "as this is run on the training data and not on the test data. Test images\n", 
          "should be reviewed to see if they meet accuracy requirements.")
    road_right_places = []
    road_wrong_places = []
    
    label_paths = {
        re.sub(r'_(lane|road)_', '_', os.path.basename(path)): path
        for path in glob(os.path.join(data_dir, 'gt_image_2', '*_road_*.png'))}
    
    for image_file in glob(os.path.join(data_dir, 'image_2', '*.png')):
        gt_image_file = label_paths[os.path.basename(image_file)]

        image = scipy.misc.imresize(scipy.misc.imread(image_file), image_shape)
        gt_image = scipy.misc.imresize(scipy.misc.imread(gt_image_file), image_shape)
        
        background_color = np.array([255, 0, 0])
        gt_bg = np.all(gt_image == background_color, axis=2)
        gt_bg = gt_bg.reshape(*gt_bg.shape, 1)
        gt_image = np.concatenate((gt_bg, np.invert(gt_bg)), axis=2)

        im_softmax = sess.run(
            [tf.nn.softmax(logits)],
            {keep_prob: 1.0, image_pl: [image]})
        prediction = im_softmax[0].reshape(image_shape[0], image_shape[1], 2)

        prediction = np.argmax(prediction, axis=-1)

        gt_image = gt_image.astype(int)

        prediction = prediction.flatten()
        road = gt_image[:,:,1].flatten()

        # Need >80% recall for road and <20% false positives of road within non-road
        tn, fp, fn, tp = confusion_matrix(road, prediction).ravel()
        recall = tp / (tp + fn)
        road_wrong_place = fp / (fp + tn)
        
        road_right_places.append(recall)
        road_wrong_places.append(road_wrong_place)

    mean_road_right = statistics.mean(road_right_places)
    mean_road_wrong = statistics.mean(road_wrong_places)
    print("Road identified as road:", mean_road_right)
    print("Non-road identified as road:", mean_road_wrong)

    assert mean_road_right >= 0.8, 'Expected at least 80% recall for road, found {}.'.format(mean_road_right)
    assert mean_road_wrong <= 0.2, 'Expected less than 20% of non-road marked as road, found {}.'.format(mean_road_wrong)