从这个例子中:https://github.com/fchollet/keras/blob/master/examples/imdb_cnn.py
得到以下代码片段。嵌入层为每个批次中的每个示例输出一个400 x 50矩阵。我的问题是1D卷积是如何工作的?它如何在400 x 50矩阵上运行?
# we start off with an efficient embedding layer which maps
# our vocab indices into embedding_dims dimensions
model.add(Embedding(max_features,
embedding_dims,
input_length=maxlen,
dropout=0.2))
# we add a Convolution1D, which will learn nb_filter
# word group filters of size filter_length:
model.add(Convolution1D(nb_filter=nb_filter,
filter_length=filter_length,
border_mode='valid',
activation='relu',
subsample_length=1))