Getting `ValueError: `logits` and `labels` must have the same shape, received ((None, 1) vs ())` err-CodePudding

I'm trying to train my model and receiving this error when I call the fit() method. Any ideas on why is this failing to run?

import pandas as pd
import tensorflow as tf

df = pd.read_csv('labeled_tweets_processed.csv')
labels = df.pop('class')
dataset = tf.data.Dataset.from_tensor_slices((df, labels))

for x, y in dataset.take(1):
  print(x, y)

import numpy as np

import tensorflow_datasets as tfds
import tensorflow as tf

tfds.disable_progress_bar()

import matplotlib.pyplot as plt

train_dataset = dataset.take(10000)
test_dataset = dataset.skip(10000)

BUFFER_SIZE = 10000
BATCH_SIZE = 32

train_dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)
test_dataset = test_dataset.batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)

VOCAB_SIZE = 1000
encoder = tf.keras.layers.TextVectorization(
    max_tokens=VOCAB_SIZE)
encoder.adapt(train_dataset.map(lambda text, label: text))

vocab = np.array(encoder.get_vocabulary()).flatten()
vocab[:20]

model = tf.keras.Sequential([
    encoder,
    tf.keras.layers.Embedding(
        input_dim=len(encoder.get_vocabulary()),
        output_dim=64,
        # Use masking to handle the variable sequence lengths
        mask_zero=True),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1)
])

model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
              optimizer=tf.keras.optimizers.Adam(1e-4),
              metrics=['accuracy'])

history = model.fit(train_dataset, validation_data=test_dataset, epochs=10)

On the last command I receive the following error: ValueError: logits and labels must have the same shape ((None, 1) vs ())

Any ideas why is this happening?

Thank you very much in advance!

CodePudding user response：

Maybe try something like this:

import pandas as pd
import tensorflow as tf

df = pd.DataFrame(data = {'texts': ['Some text', 'Some text', 'Some text', 'Some text', 'Some text'],
                          'class': [0, 0, 1, 1, 1]})

labels = df.pop('class')
dataset = tf.data.Dataset.from_tensor_slices((df, labels))

VOCAB_SIZE = 1000
encoder = tf.keras.layers.TextVectorization(
    max_tokens=VOCAB_SIZE)
encoder.adapt(dataset.map(lambda text, label: text))

BUFFER_SIZE = 2
BATCH_SIZE = 2

train_dataset = dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE).prefetch(tf.data.AUTOTUNE)

model = tf.keras.Sequential([
    encoder,
    tf.keras.layers.Embedding(
        input_dim=len(encoder.get_vocabulary()),
        output_dim=64,
        # Use masking to handle the variable sequence lengths
        mask_zero=True),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1)
])

model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
              optimizer=tf.keras.optimizers.Adam(1e-4),
              metrics=['accuracy'])

history = model.fit(train_dataset, epochs=10)