python - Tensorflow estimator ValueError: logits and labels must have the same shape ((?, 1) vs (?,))

Question

I'm relatively new to ML, thought I'll start with keras. Here I'm classifying movie reviews as positive or negative using binary crossentropy. So, when I'm trying to wrap my keras model with tensorflow estimator, I get the error:

Tensorflow estimator ValueError: logits and labels must have the same shape ((?, 1) vs (?,))

I'm using sigmoid activation as my last layer, guess I'm missing something trivial here. Any help?

from tensorflow import keras
import tensorflow as tf
print("Tensorflow {} loaded".format(tf.__version__))
import numpy as np

keras.__version__
from keras.datasets import imdb

(train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=10000)
def vectorize_sequences(sequences, dimension=10000):
    # Create an all-zero matrix of shape (len(sequences), dimension)
    results = np.zeros((len(sequences), dimension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1.  # set specific indices of results[i] to 1s
    return results.astype('float32')

# Our vectorized training data
x_train = vectorize_sequences(train_data)

# Our vectorized test data
x_test = vectorize_sequences(test_data)

# Our vectorized labels
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')

x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]

model = keras.models.Sequential()
model.add(keras.layers.Dense(16, activation='relu', input_shape=(10000,), name='reviews'))
model.add(keras.layers.Dense(16, activation='relu'))
model.add(keras.layers.Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['accuracy'])
estimator_model = keras.estimator.model_to_estimator(keras_model=model)

def input_function(features,labels=None,shuffle=False,epochs=None,batch_size=None):
    input_fn = tf.estimator.inputs.numpy_input_fn(
        x={"reviews_input": features},
        y=labels,
        shuffle=shuffle,
        num_epochs=epochs,
        batch_size=batch_size
    )
    return input_fn

estimator_model.train(input_fn=input_function(partial_x_train, partial_y_train, True,20,512))
score = estimator_model.evaluate(input_function(x_val, labels=y_val))
print(score)

Answer 1

You should reshape your labels as 2d-tensor (the first dimension will be the batch dimension and the second the scalar label):

# Our vectorized labels
y_train = np.asarray(train_labels).astype('float32').reshape((-1,1))
y_test = np.asarray(test_labels).astype('float32').reshape((-1,1))