Question

为了进行评估，我需要能够对文本数据应用卷积层。因此，我试图对亚马逊评论进行情感分析。但是，在Embedding层之后，Conv1D层将无法获得所需的形状。

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
import tensorflow as tf
print(f'Tensorflow version {tf.__version__}')
from tensorflow import keras
from tensorflow.keras.layers import Dense, Conv1D, GlobalAveragePooling1D, Embedding
import tensorflow_datasets as tfds
from tensorflow.keras.models import Model

(train_data, test_data), info = tfds.load('imdb_reviews/subwords8k',
                                          split=[tfds.Split.TRAIN, tfds.Split.TEST],
                                          as_supervised=True, with_info=True)

padded_shapes = ([None], ())

train_dataset = train_data.shuffle(25000).padded_batch(padded_shapes=padded_shapes, batch_size=16)
test_dataset = test_data.shuffle(25000).padded_batch(padded_shapes=padded_shapes, batch_size=16)

n_words = info.features['text'].encoder.vocab_size


class ConvModel(Model):
    def __init__(self):
        super(ConvModel, self).__init__()
        self.embe = Embedding(n_words, output_dim=16)
        self.conv = Conv1D(32, kernel_size=6, activation='elu')
        self.glob = GlobalAveragePooling1D()
        self.dens = Dense(2)

    def call(self, x, training=None, mask=None):
        x = self.embe(x)
        x = self.conv(x)
        x = self.glob(x)
        x = self.dens(x)
        return x

conv = ConvModel()

conv(next(iter(train_data))[0])

ValueError：conv1d_25层的输入0与该层不兼容：预期ndim = 3，找到的ndim = 2。收到完整的图形：[163，16]

如何实现这一目标，如果我错了，使用Conv1D层为文本序列输入文本的正确方法是什么？

Answer 1

它是conv(next(iter(train_dataset))[0])而不是conv(next(iter(train_data))[0])

网络结构还可以

Answer 2

词嵌入层的out_dim应该与conv1D输入过滤器大小匹配。尝试将out_dim更改为32。正确的方法：https://machinelearningmastery.com/predict-sentiment-movie-reviews-using-deep-learning/

如何在Tensorflow 2中的嵌入层之后放置Conv1D层？

2 个答案: