Why my tensorflow's model.evaluate() prints like that

Question

model.fit()

prints

60000/60000 [==============================] - 10s 175us/sample - loss: 0.4940 - accuracy: 0.8262

Which is normal. But

model.evaluate()

prints

10000/1 [======.....10000times......=====] - 1s 117us/sample - loss: 0.2859 - accuracy: 0.8578

Why?!

Answer 1

This issue is resolved in the Tensorflow Version of 2.1-rc0 .

Please find the below code, which resolves the issue:

!pip install tensorflow==2.1-rc0

import tensorflow as tf
from tensorflow import keras
print('Version of TensorFlow:', tf.__version__)
print('Version of tf.keras:', tf.keras.__version__)

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

# Build and Compile the model
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy']
             )

# Train the model
print('Training')
model.fit(train_images, train_labels, epochs=5)

# Evaluate the model
print('Evaluating')
test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=1)
print('\nTest accuracy:', test_acc)

Shown below is the screenshot of the Execution Log: