python 中的神经网络：警告：tensorflow:Model 是用形状（无，7）构建的

Question

i have data that 60 rows and nine columns from xlsx (8 columns for x and 1 columns for y). i devided it to data training 80% and data testing 20%. so i have 12 for testing and 48 for training. so i have x test, y test, x train and y train. i use neural network in python and i have this code

import tensorflow as tf
from tensorflow.keras.optimizers import Adam
model = tf.keras.models.Sequential()
adam = Adam(learning_rate=0.01)
model.add(tf.keras.layers.Dense(units=8, activation='relu')) #input ada sembilan belas
model.add(tf.keras.layers.Dense(units=4, activation='relu')) #hidden layer 19 node
model.add(tf.keras.layers.Dense(units=1, activation='linear')) #output layer tidak menggunakan aktivasi
model.compile(loss='mae', optimizer=adam)
model.fit(x_train_CWA, y_train_CWA, epochs=1000)

then i predict x test with this code

y_pred_CWA=model.predict(x_test_CWA)

After that i can predict thats data then, i want to input a new data with this code

A = float(input("A : "))
B = float(input("B: "))
C = float(input("C: "))
D = float(input ("D: "))
E = float(input ("E : "))
F = float(input ("F: "))
G = float(input ("G: "))
H = float(input ("H"))

then i entering new data and i want to predict the new data so i array the input data with this code

Prediction_CWA = np.array([A, B, C, D, E, F, G, H])

Then i predict with this code

CWA_Prediction = model.predict(Prediction_CWA)

but i found an error like this

ValueError: Exception encountered when calling layer "sequential_11" (type Sequential).

Input 0 of layer "dense_25" is incompatible with the layer: expected min_ndim=2, found ndim=1. Full shape received: (None,)

Call arguments received:
  • inputs=tf.Tensor(shape=(None,), dtype=float32)
  • training=False
  • mask=None

Answer 1

when using model.predict for a SINGLE prediction you need to expand the dimensions of the array to provide for the batch dimension so try

Prediction_CWA = np.expand_dims(Prediction_CWA, axis=0)

then do model.predict