Keras tuner error: logits and labels must have the same first dimension

Question

I'm working on my own dataset and trying to fine-tune the parameters using the Keras tuner.I'm using the basic model-building function:

from tensorflow.keras import layers
from keras_tuner import RandomSearch

def build_model(hp):
    model = keras.Sequential()
    model.add(layers.Flatten())
    model.add(
        layers.Dense(
            units=hp.Int("units", min_value=32, max_value=512, step=32),
            activation="relu",
        )
    )
    model.add(layers.Dense(10, activation="softmax"))
    model.compile(
        optimizer=keras.optimizers.Adam(
            hp.Choice("learning_rate", values=[1e-2, 1e-3, 1e-4])
        ),
        loss="categorical_crossentropy",
        metrics=["accuracy"],
    )
    return model

After showing the search space summary and trying to search the best values from the following code statement:

tuner.search(X_train, y_train, epochs=15, validation_data=(X_test, y_test))

the following error was raised:

logits and labels must have the same first dimension, got logits shape [32,10] and labels shape [6144]

I tried to change the loss to 'sparse_categorical_crossentropy' and 'categorical_crossentropy' but it didn't work.

My dataset shape is as follows:

x_test (201, 16)
y_test (201, 16, 12)
X_train (1803, 16)
y_train (1803, 16, 12)
x_val (500, 16)
y_val (500, 16, 12)

could you provide your network structure – Marco Cerliani Oct 12 '21 at 18:55 — Marco Cerliani, Oct 12 '21 at 18:55
Sure, I updated the post. – user1506515 Oct 13 '21 at 09:01 — user1506515, Oct 13 '21 at 09:01
your target is 3D while your network produces 2D output – Marco Cerliani Oct 13 '21 at 09:10 — Marco Cerliani, Oct 13 '21 at 09:10

Keras tuner error: logits and labels must have the same first dimension

0 Answers0