如何修复TensorFlow中的值错误？

Question

我用TensorFlow尝试了一些东西，但出现了以下错误：

ValueError: Input 0 of layer gru is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 3)

我怎样才能修好它

Answer 1

我可以用示例代码重现您的问题tf.keras.layers.GRU需要输入一个三维张量，形状为[batch, timesteps, feature]

复制代码

import tensorflow as tf
inputs = tf.random.normal([32, 8])
gru = tf.keras.layers.GRU(4)
output = gru(inputs)
print(output.shape)

输出

ValueError: Input 0 of layer gru_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (32, 8)

工作样本代码

import tensorflow as tf
inputs = tf.random.normal([32, 10, 8])
gru = tf.keras.layers.GRU(4)
output = gru(inputs)
print(output.shape)

输出

(32, 4)