CODEWITHSUNDEEP
pythontensorflowkeras
ManInMoon
ManInMoon

Reputation: 7005

Why am I getting Keras shape mismatch?

I am following a Keras mnist example for beginners. I have tried to change the labels to suit my own data which has 3 distinct text classifications. I am using "to_categorical" to achieve this. The shape looks right to me, but "fit" gets an error:

train_labels = keras.utils.to_categorical(train_labels, num_classes=3)

print(train_images.shape)
print(train_labels.shape)

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(3, activation=tf.nn.softmax)
])

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

model.fit(train_images, train_labels, epochs=5)

(7074, 28, 28)

(7074, 3)

Blockquote Blockquote Traceback (most recent call last): File "C:/Users/lawrence/PycharmProjects/tester2019/KeraTest.py", line 131, in model.fit(train_images, train_labels, epochs=5) File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1536, in fit validation_split=validation_split) File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 992, in _standardize_user_data class_weight, batch_size) File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1154, in _standardize_weights exception_prefix='target') File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training_utils.py", line 332, in standardize_input_data ' but got array with shape ' + str(data_shape)) ValueError: Error when checking target: expected dense_1 to have shape (1,) but got array with shape (3,)

Upvotes: 2

Views: 808

Answers (2)

Roshin Raphel
Roshin Raphel

Reputation: 2689

Use the loss, 

loss = keras.losses.categorical_crossentropy

when the target label contain multiple instances.

Upvotes: 0

Anna Krogager
Anna Krogager

Reputation: 3588

You need to use categorical_crossentropy instead of sparse_categorical_crossentropy as loss since your labels are one hot encoded.

Alternatively, you can use sparse_categorical_crossentropy if you do not one hot encode the labels. In that case, the labels should have shape (batch_size, 1).

Upvotes: 2

Related Questions