ValueError: Error when checking input: expected dense_13_input to have shape (3,) but got array with shape (1,)

Question

Im trying to predict a manually encoded data with my keras model but it doesnt work:

print(np.array([5.1, 3.5, 1.4]).shape)
prediction = model.predict(np.array([5.1, 3.5, 1.4]))

Gives me:

(3,)
ValueError: Error when checking input: expected dense_13_input to have shape (3,) but got array with shape (1,)

How can I solve this? Thanks

Marco Cerliani · Accepted Answer · 2020-05-15 09:16:29Z

2

you have to add the batch dimension (n_batch, feat_dim) ==> (1,3)

inp = Input((3))
x = Dense(10)(inp)
model = Model(inp, x)
X = np.array([5.1, 3.5, 1.4])

model.predict(X[None,:])

answered May 15, 2020 at 9:16

Marco Cerliani

22.1k3 gold badges58 silver badges61 bronze badges

Sign up to request clarification or add additional context in comments.

1 Answer 1