Why can't NumPy specify the correct size?

Question

Python

In the network, the input layer must have 4 neurons. The input must be 1 list, the length of which is 4, each element is a number.

Here is the first layer:

self.model.add(layers.Dense(4, activation = "sigmoid", input_shape=(4, )))

Here is the input:

print("SHAPE:", np.array([1, 1, 1, 1]).shape)

self.model.fit(np.array([1, 1, 1, 1]),
self.rightAnswer, 
epochs = 1,
batch_size = 1)

Here is the output:

SHAPE: (4,)

ValueError: Error when checking input: expected dense_1_input to have shape (4,) but got array with shape (1,)

Why is this happening, how to fix it?

Answer 1

Because I didn't read the documentation

# as first layer in a sequential model:
model = Sequential()
model.add(Dense(32, input_shape=(16,)))
# now the model will take as input arrays of shape (*, 16)
# and output arrays of shape (*, 32)

# after the first layer, you don't need to specify
# the size of the input anymore:
model.add(Dense(32))

https://www.tensorflow.org/api_docs/python/tf/kera...