UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer

Keras
,
1

x_train shape: (750, 1753)

 model = models.Sequential()
 model.add(layers.Dense(10, input_dim=x_train.shape[1], activation='relu'))
 model.add(layers.Dense(1, activation='sigmoid'))

Runtime warning:

/home/khteh/.local/lib/python3.12/site-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.

How to fix the warning?

3

Hi @khteh, thanks for posting this issue. When trying to build a Sequential model pass an Input object to your model, to define the input shape. This will resolve the warning.

model = models.Sequential()
model.add(layers.Input(shape=(x_train.shape[1],)))  # Specify the input shape
model.add(layers.Dense(10, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

You can read more about specifying input shapes in sequential models here.

Let me know if this works for you.

1 Like
5

Yes, it works for me. Thanks.

1 Like