Created
October 17, 2020 07:50
-
-
Save satishgunjal/2df13407784fb831e60bfbcda738abb9 to your computer and use it in GitHub Desktop.
plot_image
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def plot_image(i, predictions_array, true_label, img): | |
""" | |
This method will plot the true image and also compare the prediction with true values if matcing write the caption in green color else in red color. | |
Format is : predicted class %confidence score (true class) | |
Input: | |
i: Index of the prediction to test | |
predictions_array: Every prediction contain array of 10 number | |
true_label: Correct image labels. In case of test data they are test_labels | |
img: Test images. In case of test data they are test_images. | |
""" | |
true_label, img = true_label[i], img[i] | |
plt.grid(False) | |
plt.xticks([]) | |
plt.yticks([]) | |
plt.imshow(img, cmap=plt.cm.binary) # For grayscale colormap | |
predicted_label = np.argmax(predictions_array) | |
if predicted_label == true_label: | |
color = 'green' | |
else: | |
color = 'red' | |
plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label], | |
100*np.max(predictions_array), | |
class_names[true_label]), | |
color=color) | |
plot_image(0, predictions[0], test_labels, test_images) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment