Let us see how well our model has learnt from the train data, by testing it on the test data.
Use model.evaluate on X_test, y_test to see the test data prediction accuracy:
model.evaluate(X_test, y_test)
Let us predict and visualize the first 3 samples from the test data.
y_pred = np.argmax(model.predict(X_test[:3]), 1)
print(y_pred)
print([class_names[index] for index in y_pred])
Visualize the predictions for the first 3 samples from the test data:
plt.figure(figsize=(7, 3))
for index, image in enumerate(X_test[:3]):
plt.subplot(1, 3, index + 1)
plt.imshow(image, cmap="binary")
plt.axis('off')
plt.title(class_names[y_pred[index]], fontsize=12)
plt.subplots_adjust(wspace=0.2, hspace=0.5)
plt.show()
Note - Having trouble with the assessment engine? Follow the steps listed here
Loading comments...