ValueError while trying model.predict (5:09:41 in Part 1/2)

[DigitalizeMe]

There was a question about the dimensions of X and y, that for some reason need to be changed with the commands:
X = tf.expand_dims(X, axis=1)
y = tf.expand_dims(y, axis=1)
That works fine for the model.fit command.

But afterwards, there is another issue when I try to use the model.predict command. It results in the same error as described above, stating:

ValueError: Exception encountered when calling layer "sequential_19" (type Sequential).

Input 0 of layer "dense_22" is incompatible with the layer: expected min_ndim=2, found ndim=1. Full shape received: (None,)

So I tried this:

T = tf.constant(17.0)
T = tf.cast(tf.constant(T), dtype=tf.float32)
T = tf.expand_dims(T, axis=1)
model.predict([T])

but it didn't work.
Can you please help me solving the issue? I really want to follow along all the way through this wonderful course of yours, Mr. Bourke! Thank you very much for the effort you put into these lessons!

[xungvu2k1]

I have met this error last week.:::)). pleasezzzzz

[xungvu2k1]

All of this is active with me

Creating some datas to view and fit

import numpy as np
import matplotlib.pyplot as plt

Create features

X = np.array([-7.0, -4.0, -1.0, 2.0, 5.0, 8.0, 11.0, 14.0])

Create labels

y = np.array([3.0, 6.0, 9.0, 12.0, 15.0, 18.0, 21.0, 24.0])

Visualize

plt.scatter(X,y)

Create a demo tensor for our housing price prediction problem

house_info = tf.constant(["bedroom", "bathroom", "garage"])
house_price = tf.constant([939700])
house_info, house_price

input_shape = X.shape
output_shape = y.shape
input_shape, output_shape

Turn out Numpy arrays into tensors

X = tf.cast(tf.constant(X), dtype = tf.float32)
y = tf.cast(tf.constant(y), dtype = tf.float32)
X = tf.expand_dims(X, axis=1)
y = tf.expand_dims(y, axis=1)

Set random seed

tf.random.set_seed(42)

1. Create a model using the Sequential API

model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(1)) # predict one number from input one number

2. Compile the model

model.compile(loss=tf.keras.losses.mae, #mae is short for mean absolute error
optimizer = tf.keras.optimizers.SGD(),
metrics = ["mae"])

3. fit the model

model.fit(X, y, epochs = 5)

#Check out X and y
X,y

c = np.array([17])
c = tf.cast(tf.constant(c), dtype = tf.float32)
c = tf.expand_dims(c, axis = 0)

model.predict(c)

[moayadeldin]

try to define an input layer within the input shape

model = tf.keras.Sequential([
tf.keras.layers.Input(shape=(1,)),
tf.keras.layers.Dense(1)

])

[pravincoder]

The Corrected code :-

Fit Model

#Set Random Seed
tf.random.set_seed(42)

#Create a model using Sequential API
model= tf.keras.Sequential([tf.keras.layers.Dense(1,input_shape=(1,))])

#Compile the model
model.compile(loss=tf.keras.losses.mae,optimizer=tf.keras.optimizers.SGD(), metrics=['mae'])

#Fit the model
model.fit(X,Y,epochs=5)

@xungvu2k1
@DigitalizeMe