如何改变角点Conv1D卷积误差的输入维数形状？
如何改变角点Conv1D卷积误差的输入维数形状？
提问于 2022-05-21 20:47:43
我有一个二元分类问题。我想包括一个Conv1D层，但在从3D (https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv1D)中改变输入形状的输入形状时遇到了麻烦。
所以我的代码是
#Hyperparameters
EMBEDDING_DIM = 50
MAXLEN = 500 #1000, 1400
VOCAB_SIZE = 33713
DENSE1_DIM = 64
DENSE2_DIM = 32
LSTM1_DIM = 32
LSTM2_DIM = 16
WD = 0.001
FILTERS = 64
KERNEL_SIZE = 5
# Stacked hybrid model
model_lstm = tf.keras.Sequential([
tf.keras.layers.Embedding(VOCAB_SIZE+1, EMBEDDING_DIM, input_length=MAXLEN,weights=[EMBEDDINGS_MATRIX], trainable=False),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(LSTM1_DIM, dropout=0.5, kernel_regularizer = regularizers.l2(WD), return_sequences=True)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(LSTM2_DIM, dropout=0.5, kernel_regularizer = regularizers.l2(WD))),
tf.keras.layers.Dense(DENSE2_DIM, activation='relu'),
# tf.keras.layers.Conv1D(FILTERS, KERNEL_SIZE, activation='relu'),
# tf.keras.layers.Dropout(0.1),
# tf.keras.layers.GlobalAveragePooling1D(),
# tf.keras.layers.Dense(1, activation='sigmoid')
])
...它给出了这个总结
Model: "sequential_6"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_10 (Embedding) (None, 500, 50) 1685700
bidirectional_19 (Bidirecti (None, 500, 64) 21248
onal)
bidirectional_20 (Bidirecti (None, 32) 10368
onal)
dense_11 (Dense) (None, 32) 1056
=================================================================
Total params: 1,718,372
Trainable params: 32,672
Non-trainable params: 1,685,700因此，如果我使用Conv1D层，就会得到以下错误：
ValueError: Input 0 of layer "conv1d_4" is incompatible with the layer: expected min_ndim=3, found ndim=2. Full shape received: (None, 32)例如，我尝试过将input_shape = (None，16，32)作为Conv1D层中的一个参数，但它不是这样工作的。
谢谢。
回答 1
Stack Overflow用户
发布于 2022-06-10 17:09:00
您可以添加tf.keras.layers.Reshape层来更改数据的形状，如下所示。
EMBEDDING_DIM = 50
MAXLEN = 500 #1000, 1400
VOCAB_SIZE = 33713
DENSE1_DIM = 64
DENSE2_DIM = 32
LSTM1_DIM = 32
LSTM2_DIM = 16
WD = 0.001
FILTERS = 64
KERNEL_SIZE = 5
EMBEDDINGS_MATRIX = np.zeros((VOCAB_SIZE+1, EMBEDDING_DIM))
# Stacked hybrid model
model_lstm = tf.keras.Sequential([
tf.keras.layers.Embedding(VOCAB_SIZE+1, EMBEDDING_DIM, input_length=MAXLEN,weights=[EMBEDDINGS_MATRIX], trainable=False),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(LSTM1_DIM, dropout=0.5, kernel_regularizer = tf.keras.regularizers.L1(WD), return_sequences=True)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(LSTM2_DIM, dropout=0.5, kernel_regularizer = tf.keras.regularizers.L1(WD))),
tf.keras.layers.Dense(DENSE2_DIM, activation='relu'),
tf.keras.layers.Reshape((32,1)),
tf.keras.layers.Conv1D(FILTERS, KERNEL_SIZE, activation='relu'),
tf.keras.layers.Dropout(0.1),
tf.keras.layers.GlobalAveragePooling1D(),
tf.keras.layers.Dense(1, activation='sigmoid')
])
model_lstm.summary()输出如下。
Model: "sequential_14"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_16 (Embedding) (None, 500, 50) 1685700
bidirectional_8 (Bidirectio (None, 500, 64) 21248
nal)
bidirectional_9 (Bidirectio (None, 32) 10368
nal)
dense_15 (Dense) (None, 32) 1056
reshape_3 (Reshape) (None, 32, 1) 0
conv1d (Conv1D) (None, 28, 64) 384
=================================================================
Total params: 1,718,756
Trainable params: 33,056
Non-trainable params: 1,685,700
_________________________________________________________________页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/72333117
复制相关文章
相似问题
腾讯云开发者
