Keras functional api input shape

Question

My model definition is:

inputs = keras.Input(shape=(28,28))
dense = keras.layers.Dense(64, activation="relu")
x = dense(inputs)
x = keras.layers.Dense(64, activation="relu")(x)
outputs = keras.layers.Dense(10)(x)
model = keras.Model(inputs=inputs, outputs=outputs, name="mnist_model")

And I will train the network with:

model.compile(optimizer="sgd", loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])
history = model.fit(x_train, y_train, batch_size=10, epochs=30, verbose=2)

which x_train's shape is (55000, 28, 28) and y_train's shape is (55000,) and I get this error:

ValueError: Shape mismatch: The shape of labels (received (10, 1)) should equal the shape of logits except for the last dimension (received (10, 28, 10))

you miss a Flatten layer in your network to pass from 3D to 2D — Marco Cerliani
– Marco Cerliani, Commented Dec 27, 2020 at 23:43

DachuanZhao · Accepted Answer · 2020-12-29 02:04:29Z

1

What @Marco Cerliani said means you should change your code to

inputs = keras.Input(shape=(28,28))
output = keras.layers.Flatten()(inputs)
output = keras.layers.Dense(64, activation="relu")(output)
output = keras.layers.Dense(64, activation="relu")(output)
outputs = keras.layers.Dense(10)(output)
model = keras.Model(inputs=inputs, outputs=outputs, name="mnist_model")

Please read the tensorflow tutorials and guide if you're a beginner . You will find the answer of your question if you read this .

answered Dec 29, 2020 at 2:04

DachuanZhao

1,3594 gold badges20 silver badges38 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Keras functional api input shape

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related