opencv - Simple Neural Network in Python not displaying label for the test image -

i followed tutorial learn how create simple neural network using python. below code:

def image_to_feature_vector(image, size=(32,32)):     return cv2.resize(image, size).flatten()  ap = argparse.argumentparser() ap.add_argument("-d", "--dataset", required=true,     help="path input dataset") args = vars(ap.parse_args())   print("[info] describing images...") imagepaths = list(paths.list_images(args["dataset"])) print(imagepaths) #this list of image paths   # initialize data matrix , labels list data = [] labels = []  (i, imagepath) in enumerate(imagepaths):     image = cv2.imread(imagepath)     label = imagepath.split(os.path.sep)[-1].split(".")[0]      features = image_to_feature_vector(image)     data.append(features)     labels.append(label)      # show update every 1,000 images     if > 0 , % 1000 == 0:         print("[info] processed {}/{}".format(i, len(imagepaths)))  # encode labels, converting them strings integers le = labelencoder() labels = le.fit_transform(labels)  data = np.array(data) / 255.0 labels = np_utils.to_categorical(labels, 2)  print("[info] constructing training/testing split...") (traindata, testdata, trainlabels, testlabels) = train_test_split(     data, labels, test_size=0.25, random_state=42)  #constructing neural network model = sequential() model.add(dense(768, input_dim=3072, init="uniform",     activation="relu")) model.add(dense(384, init="uniform", activation="relu")) model.add(dense(2)) model.add(activation("softmax"))  # train model using sgd print("[info] compiling model...") sgd = sgd(lr=0.01) model.compile(loss="binary_crossentropy", optimizer=sgd,     metrics=["accuracy"]) model.fit(traindata, trainlabels, nb_epoch=50, batch_size=128)  #test model # show accuracy on testing set print("[info] evaluating on testing set...") (loss, accuracy) = model.evaluate(testdata, testlabels,     batch_size=128, verbose=1) print("[info] loss={:.4f}, accuracy: {:.4f}%".format(loss,     accuracy * 100)) 

the last few lines run trained neural network against testing set , displays accuracy follows:

but, there way instead of testing set, supply path of image , tells whether cat or dog (this tutorial used cat/dog sample, using now). how do in above code? thanks.

keras models have predict method .

predictions = model.predict(images_as_numpy_array) 

will give predictions on chosen data. have opened , transformed image numpy array. did training , testing set following lines:

image = cv2.imread(imagepath) label = imagepath.split(os.path.sep)[-1].split(".")[0] features = image_to_feature_vector(image)