CODEWITHSUNDEEP
pythontensorflowkerasdeep-learning
random student
random student

Reputation: 775

why val_loss and val_accuracy not showing in epochs

I'm trying to classify images whether they're cats,dogs or pandas. the data contains all of images (cats + dogs + pandas) and the labels contains the labels of them but somehow when i fit the data to the model, the val_loss and val_accuracy does not show up, the only metrics shown in each epochs are loss and accuracy. I have no clue why it's not showing up but i have feeling that it's because i don't pass validation_data so i passed X_test.all() into validation_data but the val_loss and val_accuracy still does not show up, what should i do?

data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)

X_train, X_test, y_train, y_test = train_test_split(data, labels, test_size=0.2)

model = tf.keras.models.Sequential([
  tf.keras.layers.Conv2D(32, (2,2), activation = 'relu', input_shape= (height, width, n_channels)),
  tf.keras.layers.MaxPooling2D(2,2),
  tf.keras.layers.Conv2D(64,(2,2), activation= 'relu'),
  tf.keras.layers.MaxPooling2D(2,2),
  tf.keras.layers.Conv2D(128,(2,2), activation= 'relu'),
  tf.keras.layers.MaxPooling2D(2,2),
  tf.keras.layers.Conv2D(256,(2,2), activation= 'relu'),
  tf.keras.layers.MaxPooling2D(2,2),
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(512, activation= 'relu'),
  tf.keras.layers.Dense(3, activation= 'softmax')
])

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

y_train = np_utils.to_categorical(y_train, 3)

model.fit(X_train, y_train, batch_size=32, epochs=25, verbose=1)

Upvotes: 2

Views: 7449

Answers (2)

ashraful16
ashraful16

Reputation: 2782

you forget to convert y_test variable to categorical type. Add this line,

y_test  = np_utils.to_categorical(y_test  , 3)

Upvotes: 1

Vinayak Mikkal
Vinayak Mikkal

Reputation: 87

You forgot to input validation test in your model fit.

model.fit(X_train, y_train, batch_size=32, epochs=25, verbose=1, validation_data=(X_test,y_test))

Upvotes: 5

Related Questions