lecture #234 - fails with 'ValueError: logits and labels must have the same shape, received ((None, 15, 1) vs (None,)'

[biologiccarbon]

using tensorflow 2.11.0
the lecture titled " Model 1: Building, fitting and evaluating our first deep model on text data"

fitting the 'feed forward neural network' fails with error

ValueError: logitsandlabels must have the same shape, received ((None, 15, 1) vs (None,)

if appears you now must have the following line (as per your notes but not shown in lecture)

x = layers.GlobalAveragePooling1D()(x)

[liltimtim]

Can also confirm the error received as well.

tf.__version__ #yields 2.15.0

Code Before Change

from tensorflow.keras import layers
inputs = layers.Input(shape=(1,), dtype="string")
x = text_vectorizer(inputs) # string -> number
x = embedding(x) # number -> dense vector
outputs = layers.Dense(1, activation="sigmoid")(x)

#compile the model
model_1 = tf.keras.Model(inputs, outputs)
model_1.compile(loss="binary_crossentropy",
                optimizer=tf.keras.optimizers.Adam(),
                metrics=["accuracy"])

# fit the model
history_1 = model_1.fit(x=train_sentences, y=train_labels, epochs=5, validation_data=(val_sentences, val_labels))

Working Code with Change

from tensorflow.keras import layers
inputs = layers.Input(shape=(1,), dtype="string")
x = text_vectorizer(inputs) # string -> number
x = embedding(x) # number -> dense vector
x = layers.GlobalAveragePooling1D()(x)
outputs = layers.Dense(1, activation="sigmoid")(x)

#compile the model
model_1 = tf.keras.Model(inputs, outputs)
model_1.compile(loss="binary_crossentropy",
                optimizer=tf.keras.optimizers.Adam(),
                metrics=["accuracy"])

# fit the model
history_1 = model_1.fit(x=train_sentences, y=train_labels, epochs=5, validation_data=(val_sentences, val_labels))

Error you receive from colab

Epoch 1/5

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

[<ipython-input-118-2ee86a25223c>](https://localhost:8080/#) in <cell line: 15>()
     13 
     14 # fit the model
---> 15 history_1 = model_1.fit(x=train_sentences, y=train_labels, epochs=5, validation_data=(val_sentences, val_labels))

1 frames

[/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py](https://localhost:8080/#) in tf__train_function(iterator)
     13                 try:
     14                     do_return = True
---> 15                     retval_ = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
     16                 except:
     17                     do_return = False

ValueError: in user code:

    File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1401, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1384, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1373, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1151, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/training.py", line 1209, in compute_loss
        return self.compiled_loss(
    File "/usr/local/lib/python3.10/dist-packages/keras/src/engine/compile_utils.py", line 277, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "/usr/local/lib/python3.10/dist-packages/keras/src/losses.py", line 143, in __call__
        losses = call_fn(y_true, y_pred)
    File "/usr/local/lib/python3.10/dist-packages/keras/src/losses.py", line 270, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "/usr/local/lib/python3.10/dist-packages/keras/src/losses.py", line 2532, in binary_crossentropy
        backend.binary_crossentropy(y_true, y_pred, from_logits=from_logits),
    File "/usr/local/lib/python3.10/dist-packages/keras/src/backend.py", line 5822, in binary_crossentropy
        return tf.nn.sigmoid_cross_entropy_with_logits(

    ValueError: `logits` and `labels` must have the same shape, received ((None, 15, 1) vs (None,)).

[Friend09]

my working solution: I used a flatten layer before the Dense layer and it worked

# inputs = layers.Input(shape=(1,), dtype="string")
# x = text_vectorizer(inputs)
# x = embedding(x)
# # x = layers.GlobalAveragePooling1D()(x)
# x = layers.Flatten()(x)
# outputs = layers.Dense(1, activation="sigmoid")(x)

# model_1 = tf.keras.Model(inputs, outputs, name="model_1_dense")

# model_1.compile(loss="binary_crossentropy", optimizer=tf.keras.optimizers.Adam(),metrics=["accuracy"])
# model_1.summary()```