516c2a4c7e8f92e1ea299e966215c2ffe4c5b980,cifar10.py,,,#,14

Before Change

                   nb_val_samples=testX.shape[0], verbose=1)

scores = model.evaluate_generator(test_generator.flow(testX, testY, nb_epoch), testX.shape[0])
print("Accuracy = %f" % (100 * scores[1]))
print("Error = %f" % (100 - 100 * scores[1]))

After Change

(trainX, trainY), (testX, testY) = cifar10.load_data()

trainX = trainX.astype("float32")
testX = testX.astype("float32")

trainX /= 255.
testX /= 255.

Y_train = np_utils.to_categorical(trainY, nb_classes)
Y_test = np_utils.to_categorical(testY, nb_classes)

generator = ImageDataGenerator(rotation_range=15,
                               width_shift_range=5./32,
                               height_shift_range=5./32)

generator.fit(trainX, seed=0)

// Load model
model.load_weights("weights/DenseNet-40-12-CIFAR10.h5")
print("Model loaded.")

// model.fit_generator(generator.flow(trainX, Y_train, batch_size=batch_size), samples_per_epoch=len(trainX), nb_epoch=nb_epoch,
//                    callbacks=[ModelCheckpoint("weights/DenseNet-40-12-CIFAR10.h5", monitor="val_acc", save_best_only=True,
//                                               save_weights_only=True)],
//                    validation_data=(testX, Y_test),
//                    nb_val_samples=testX.shape[0], verbose=2)

yPreds = model.predict(testX)
yPred = np.argmax(yPreds, axis=1)
yTrue = testY

accuracy = metrics.accuracy_score(yTrue, yPred) * 100
error = 100 - accuracy
print("Accuracy : ", accuracy)
print("Error : ", error)

Instances