我如何将参差不齐的张量输入到keras模型中，以便它可以编译和预测而不会出现输入错误？

Question

我正在将tensorflow 2.1与ipython3一起使用。

from tensorflow import keras
from tensorflow.keras import layers
import tensorflow as tf
import tensorflow_text as text


array1 = [4.378686935524456e-05, 5.838137076352723e-05, 7.29753082850948e-05, -1.751480704115238e-05, -0.00014302860654424876]

array2 = [8.178586925524456e-05, 2.638037056352723e-05, 3.49752081850948e-05]

array3 = [5.3793552445628684e-05, 1.8381229370763528e-05, 2.23082850949758e-05, -3.041157514807238e-05, -0.0006544248754302861]

array4 = [8.380704135524457e-05, 2.606544076352723e-05]

mydata = tf.ragged.constant([[ array1], [ array2], [array3], [array4]])

model = tf.keras.Sequential([
  tf.keras.layers.InputLayer(input_shape=(None,), dtype='float64', ragged=True),
  text.keras.layers.ToDense(pad_value=0, mask=True),   
  tf.keras.layers.Embedding(100, 16),
  tf.keras.layers.LSTM(32),
  tf.keras.layers.Dense(32, activation='relu'),
  tf.keras.layers.Dense(1, activation='sigmoid')
])

model.compile(
  optimizer="rmsprop",
  loss="binary_crossentropy",
  metrics=["accuracy"])

output = model.predict(mydata)  #XXX
print(output)

tf.RaggedTensor [[[4.378686935524456e-05, 5.838137076352723e-05, 7.29753082850948e-05, -1.751480704115238e-05, -0.00014302860654424876]], [[8.178586925524456e-05, 2.638037056352723e-05, 3.49752081850948e-05]], [[5.3793552445628684e-05, 1.8381229370763528e-05, 2.23082850949758e-05, -3.041157514807238e-05, -0.0006544248754302861]], [[8.380704135524457e-05, 2.606544076352723e-05]]]

数据类型：dtype: 'float64'

mydata的参差不齐的张量形状：(4, None, None)

我得到的错误是：

ValueError: Error when checking input: expected input_4 to have 2 dimensions, but got array with shape (4, None, None)

Answer 1

[当定义参差不齐的张量时，您需要删除方括号：

mydata = tf.ragged.constant([array1,  array2, array3, array4])

这是错误的意思。