Cannot see all `Dense` layer info from `search_space_summary()` when using `RandomSearch Tuner` in Keras-Tuner?

Question

I am trying to use keras-tuner to tune hyperparameters, like

!pip install keras-tuner --upgrade
import keras_tuner as kt
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.optimizers import Adam

def build_model(hp):
    model = Sequential([
        Flatten(input_shape=(28, 28)),
        Dense(units= hp.Int('units', min_value = 16, max_value = 64, step = 16), activation='relu'),
        Dense(units = hp.Int('units', min_value = 8, max_value = 20, step = 2), activation='softmax')
    ])

    model.compile(
        optimizer=Adam(learning_rate=hp.Float('learning_rate', min_value=1e-4, max_value=1e-2, sampling='LOG')),
        loss='sparse_categorical_crossentropy',
        metrics=['accuracy']
    )
    return model

# Create a RandomSearch Tuner
tuner = kt.RandomSearch(
    build_model, 
    objective='val_accuracy',
    max_trials=10,
    executions_per_trial=2
)

# Display a summary of the search space
tuner.search_space_summary()

shows

Search space summary
Default search space size: 2
units (Int)
{'default': None, 'conditions': [], 'min_value': 16, 'max_value': 64, 'step': 16, 'sampling': 'linear'}
learning_rate (Float)
{'default': 0.0001, 'conditions': [], 'min_value': 0.0001, 'max_value': 0.01, 'step': None, 'sampling': 'log'}

However, when checking the search_space_summary() output, only the 1st Dense layer is shown in the summary, while the information about the 2nd Dense layer, i.e., Dense(units = hp.Int('units', min_value = 8, max_value = 20, step = 2), activation='softmax'), is not seen.

Did I misconfigured something or it is supposed to yield the output like that? Could anyone help me to understand why it outputs the summary like this?

xdurch0 · Accepted Answer · 2025-04-15 09:43:58Z

2

Each hyperparameter must have a unique name. This is also listed in the docs. In your case, both layer units parameters are called units . You should rename them to something like units_1 and units_2, for example.

edited Apr 15 at 9:43

answered Apr 15 at 6:00

xdurch0

10.6k4 gold badges39 silver badges46 bronze badges

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

3 Comments

ThomasIsCoding Apr 15 at 7:15

aha, you are right. thanks for the reference, now I see why i had that problem!

xdurch0 Apr 15 at 9:44

Well it would probably be better if trying to do this threw an error, instead of silently ignoring the second parameter...

ThomasIsCoding Apr 15 at 11:10

yes, error or warning would be great

Collectives™ on Stack Overflow

Cannot see all `Dense` layer info from `search_space_summary()` when using `RandomSearch Tuner` in Keras-Tuner?

1 Answer 1

3 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

3 Comments

Your Answer

Sign up or log in

Post as a guest

Related