WARNING:tensorflow:Model was constructed with shape (None, 188) for input, but it was called on an i-CodePudding

Home > Enterprise > WARNING:tensorflow:Model was constructed with shape (None, 188) for input, but it was called on an i

WARNING:tensorflow:Model was constructed with shape (None, 188) for input, but it was called on an i

Time：07-08

Can someone help me to fix this? tensorflow is really annoying.

WARNING:tensorflow:Model was constructed with shape (None, 188) for input KerasTensor(type_spec=TensorSpec(shape=(None, 188), dtype=tf.float32, name='input_9'), name='input_9', description="created by layer 'input_9'"), but it was called on an input with incompatible shape (188,).

CodePudding user response：

You seem to be missing a dimension. Try batching your data:

train_set = train_set.batch(32)

Page link：https//www.codepudding.com/Enterprise/467698.html

Prev:Need to increase the accuracy of my LSTM model

Next:How do I await code inside a method that returns an EitherAsync<T1, T2> in LanguageExt?

Tags：

python

tensorflow

keras

Links：
CodePudding