Tensorflow 估计器 ValueError:logits 和标签必须具有相同的形状 ((?, 1) vs (?,)) [英] Tensorflow estimator ValueError: logits and labels must have the same shape ((?, 1) vs (?,))

问题描述

我对 ML 比较陌生，以为我会从 keras 开始.在这里，我使用二元交叉熵将电影评论分类为正面或负面.因此，当我尝试使用 tensorflow estimator 包装我的 keras 模型时，出现错误:

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 和标签必须具有相同的形状 ((?, 1) vs (?,))

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

我使用 sigmoid 激活作为我的最后一层，我猜我在这里遗漏了一些微不足道的东西.有什么帮助吗?

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)

推荐答案

你应该将你的标签重塑为二维张量(第一个维度是批量维度，第二个维度是标量标签):

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))

这篇关于Tensorflow 估计器 ValueError:logits 和标签必须具有相同的形状 ((?, 1) vs (?,))的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！