def build_model(hp):
model = keras.Sequential()
for i in range(hp.Int('input_shape', 2, 20)):
    model.add(layers.Dense(units=hp.Int('units_'   str(i),
                                        min_value=32,
                                        max_value=512,
                                        step=32),
                           activation='relu'))
model.add(layers.Dense(2, activation='sigmoid'))
model.compile(
    optimizer=keras.optimizers.Adam(
        hp.Choice('learning_rate', [1e-2, 1e-3, 1e-4])),
    loss='binary_crossentropy',
    metrics=['accuracy'])
return model

tuner.search(X_train, y_train,
         epochs=5,
         validation_data=(X_test, y_test))

ValueError: in user code:

File "/home/user/miniconda3/lib/python3.9/site-packages/keras/engine/training.py", line 1051, in train_function  *
    return step_function(self, iterator)
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/engine/training.py", line 1040, in step_function  **
    outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/engine/training.py", line 1030, in run_step  **
    outputs = model.train_step(data)
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/engine/training.py", line 890, in train_step
    loss = self.compute_loss(x, y, y_pred, sample_weight)
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/engine/training.py", line 948, in compute_loss
    return self.compiled_loss(
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/engine/compile_utils.py", line 201, in __call__
    loss_value = loss_obj(y_t, y_p, sample_weight=sw)
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/losses.py", line 139, in __call__
    losses = call_fn(y_true, y_pred)
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/losses.py", line 243, in call  **
    return ag_fn(y_true, y_pred, **self._fn_kwargs)
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/losses.py", line 1930, in binary_crossentropy
    backend.binary_crossentropy(y_true, y_pred, from_logits=from_logits),
File "/home/user/miniconda3/lib/python3.9/site-packages/keras/backend.py", line 5283, in binary_crossentropy
    return tf.nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)

ValueError: `logits` and `labels` must have the same shape, received ((None, 2) vs (None, 1)).

Please help me solve the above error. Which is : ValueError: logits and labels must have the same shape, received ((None, 2) vs (None, 1)). I am doing Binary Classification here.

CodePudding user response：

When using binary_crossentropy you need to write the last Dense layer like below:

layers.Dense(1, activation='sigmoid')

Full code for finding the best parameter with keras-tuner:

# !pip install keras-tuner -q

import numpy as np
import keras_tuner
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

(x_train, y_train), (x_test, y_test) = ((np.random.rand(1000,4), np.random.randint(0, 2, 1000)) , 
                                        (np.random.rand(100,4), np.random.randint(0,2, 100)))


def build_model(hp):
    model = keras.Sequential()
    n_layers = 4
    n_features = x_train.shape[1]
    inputs = model.add(keras.Input(shape=(n_features,)))

    for i in range(hp.Int("dense_layer", 1, n_layers)):
        model.add(layers.Dense(units=hp.Int('units_'   str(i),
                                            min_value=32,
                                            max_value=512,
                                            step=32),
                            activation='relu'))
    model.add(layers.Dense(1, activation='sigmoid'))
    model.compile(
        optimizer=keras.optimizers.Adam(
            hp.Choice('learning_rate', [1e-2, 1e-3, 1e-4])),
        loss='binary_crossentropy',
        metrics=['accuracy'])
    return model



hp = keras_tuner.HyperParameters()
model = build_model(hp)
model.summary()
tuner = keras_tuner.RandomSearch(
    build_model,
    max_trials=10,
    overwrite=True,
    objective="val_accuracy",
    # Set a directory to store the intermediate results.
    directory="/logs/hyp_tune/",
)

tensorboard_cb = tf.keras.callbacks.TensorBoard('/logs/hyp_tune/')
tuner.search(
    x_train, y_train,
    validation_data=(x_test, y_test),
    epochs=5,
    callbacks=[tensorboard_cb],
)

Output:

%load_ext tensorboard
%tensorboard --logdir /logs/hyp_tune/

CodePudding user response：

Binary Crossentropy loss expects the model to output a single floating-point value. Your model seems to be outputting 2. Change the last layer of your model to output a single value like so:

model.add(layers.Dense(1, activation='sigmoid'))