Print shows no result displays "Typeerror: 'float' Object is not iterable"

Question

I am making the code of a video lesson of Tensorflow but my code for more q is equal does not give the same result

Everything that appears in the terminal:

Windows PowerShell
Copyright (C) Microsoft Corporation. Todos os direitos reservados.

Experimente a nova plataforma cruzada PowerShell https://aka.ms/pscore6

PS D:\Curso IA> & "D:/Program Files (x86)/Microsoft Visual Studio/Shared/Python37_64/python.exe" "d:/Curso IA/aulaTensorFlow.py"
2020-06-04 16:07:37.196750: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-06-04 16:07:37.207068: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
  File "d:/Curso IA/aulaTensorFlow.py", line 16, in <module>
    keras.layers.Flatten(input_shape=(28.28)),
  File "C:\Users\lucas\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\layers\core.py", line 630, in __init__
    super(Flatten, self).__init__(**kwargs)
  File "C:\Users\lucas\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\training\tracking\base.py", line 456, in _method_wrapper   
    result = method(self, *args, **kwargs)
  File "C:\Users\lucas\AppData\Roaming\Python\Python37\site-packages\tensorflow\python\keras\engine\base_layer.py", line 373, in __init__
    batch_input_shape = (batch_size,) + tuple(kwargs['input_shape'])
TypeError: 'float' object is not iterable

Code:

import tensorflow as tf
from tensorflow import keras
import numpy as np 
import matplotlib.pyplot as plt 

banco_de_imagens = keras.datasets.fashion_mnist

(train_images, trains_labels), (test_images, test_labels) = banco_de_imagens.load_data()

class_names = ['t_shirt','trouser','pullover','dress','coat','sandal','shirt','sneaker','bag','boot']

train_images = train_images / 255.0 
test_images = test_images / 255.0

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28.28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metric=['accuracy'])

model.fit(train_images, trains_labels, epochs=5)


predictions = model.predict(test_images)

print(predictions[0])