Undefined function on TensorFlow MNIST Image Classification Project

TensorFlow General Discussion
1

I was working with Tensorflow’s MNIST Image Classification project link: (Basic classification: Classify images of clothing  |  TensorFlow Core), and during verify predictions phase, this code stated that plot_value_array was not defined even though I followed everything according to the tutorial that can be accessed, tried to work with the problem but I had no success finding a solution

#Verify predictions

i = 0

plt.figure(figsize=(6,3))

plt.subplot(1,2,1)

plot_image(i, predictions[i], test_labels, test_images)

plt.subplot(1,2,2)

plot_value_array(i, predictions[i], test_labels)

plt.show()
3

If you use Colab the most likely issue would be that you need to re-run the cell that defines the function

4

Hi @Ata_Tekeli, I have executed the code in the colab but i did not face error. Could you please share the error you are facing. Thank You.

6

It says plot_value_array is not defined

7

Hi @Ata_Tekeli, There is a function defined for plot_value_array

def plot_value_array(i, predictions_array, true_label):
  true_label = true_label[i]
  plt.grid(False)
  plt.xticks(range(10))
  plt.yticks([])
  thisplot = plt.bar(range(10), predictions_array, color="#777777")
  plt.ylim([0, 1])
  predicted_label = np.argmax(predictions_array)

  thisplot[predicted_label].set_color('red')
  thisplot[true_label].set_color('blue')

You have to execute this function before your code. Thank You.