CODEWITHSUNDEEP
pythonpython-3.xtensorflowmachine-learningneural-network
Vishal Pallikonda
Vishal Pallikonda

Reputation: 161

'TypeError: Invalid shape (10000, 28, 28) for image data' in tensor flow Fashion MNIST image prediction

I was following the Fashion MNIST image prediction tutorial on TensorFlow; built and trained the model, but after writing the functions to plot the predictions and while attempting to plot the predicted image, it throws the error:

TypeError: Invalid shape (10000, 28, 28) for image data

The entire code:

import tensorflow as tf
import numpy as np
from tensorflow import keras
import matplotlib.pyplot as plt

fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 
'Sneaker', 'Bag', 'Ankle boot']

plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid = False

train_images = train_images/255
test_images = test_images/255

plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid=False
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])

model = keras.Sequential([keras.layers.Flatten(input_shape=(28,28)),keras.layers.Dense(128, 
activation ='relu'),keras.layers.Dense(10)])



model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics=['accuracy'])

model.fit(train_images, train_labels, epochs=50)

test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)
print('Test Accuracy:', test_acc)

probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()])
predictions = probability_model.predict(test_images)

predictions[0]

np.argmax(predictions[0])

def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_labels, image=predictions_array, true_label[i], img[i]
    plt.grid=False
    plt.xticks([])
    plt.yticks([])

    plt.imshow(img, cmap=plt.cm.binary)
    predicted_label = np.argmax(predictions_array)

    if predicted_label == true_label:
        color = 'blue'
    else:
        color = 'red'
    
    plt.xlabel('{}{:2.0f}%({})'.format(class_names[predicted_label], 100*np.max[predictions_array], class_names[true_label]),color=color)

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

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

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)

Upvotes: 1

Views: 370

Answers (1)

Marco Cerliani
Marco Cerliani

Reputation: 22021

here the correct plot function:

def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_labels, img = predictions_array, true_label[i], img[i]
    plt.grid=False
    plt.xticks([])
    plt.yticks([])

    plt.imshow(img, cmap=plt.cm.binary)
    predicted_label = np.argmax(predictions_array)

    if predicted_label == true_labels:
        color = 'blue'
    else:
        color = 'red'
    
    print(class_names[predicted_label], 100*np.max(predictions_array), class_names[true_labels])

    plt.xlabel('{}{:2.0f}%({})'.format(class_names[predicted_label], 100*np.max(predictions_array), class_names[true_labels]), color=color)

working example: https://colab.research.google.com/drive/1owyRzS5lRW6DDc3p7D13D8Ih0yoj6Rz5?usp=sharing

Upvotes: 1

Related Questions