Проблема в путанице матрицы, где FP и TN приходит 0

Question

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Convolution2D
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dense
import numpy as np 
from sklearn.metrics import classification_report, confusion_matrix

#Initialising the CNN
classifier = Sequential()

#step_1:Convolution
classifier.add(Convolution2D(32,3,padding='same', input_shape=(64,64,3),activation='relu'))

#Step_2: Pooling
classifier.add(MaxPooling2D(pool_size=(2,2)))

#Adding a second convolutional layer
classifier.add(Convolution2D(32,3,activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2,2)))

#Adding a third convolutional layer
classifier.add(Convolution2D(64,3,activation='relu'))
classifier.add(MaxPooling2D(pool_size=(2,2)))

#Step_3: Flatten
classifier.add(Flatten())

#Step_3: Full_Connection
classifier.add(Dense(activation="relu", units=128))
classifier.add(Dense(activation="sigmoid", units=1))

#Step_4: Compiling the CNN
classifier.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

#Step_5: Fitting the CNN to the image
from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1./255)

training_set = train_datagen.flow_from_directory(
        r'D:\dataset1\training_set',
        target_size=(64, 64),
        batch_size=32,
        class_mode='binary'
        )


validation_generator = test_datagen.flow_from_directory(
        r'D:\dataset1\test_set',
        target_size=(64, 64),
        batch_size=32,
        class_mode='binary',
        shuffle= False
        )

#validation_generator = test_datagen.flow_from_directory(
        #r'D:\dataset\single_prediction',
        #target_size=(64, 64),
        #batch_size=32,
        #class_mode='binary')

classifier.fit_generator(
        training_set,
        steps_per_epoch=24000//32,
        epochs=1,
        validation_data=validation_generator,
        validation_steps=8000)

#Confution Matrix and Classification Report
Y_pred = classifier.predict_generator(validation_generator)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(len(y_pred))
print(len(validation_generator.classes))
print(confusion_matrix(validation_generator.classes, y_pred))
print('Classification Report')
target_names = ['Cracked', 'NotCracked']
print(classification_report(validation_generator.classes, y_pred, target_names=target_names))

Вывод:

Found 24000 images belonging to 2 classes.
Found 8000 images belonging to 2 classes.
24000/24000 [==============================] - 10432s 435ms/step - loss: 0.0155 - accuracy: 0.9952 - val_loss: 0.0107 - val_accuracy: 0.9976
Confusion Matrix
8000
8000
[[4000    0]
 [4000    0]]
Classification Report
C:\Users\Dell\Anaconda3\lib\site-packages\sklearn\metrics\classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.
  'precision', 'predicted', average, warn_for)
              precision    recall  f1-score   support

     Cracked       0.50      1.00      0.67      4000
  NotCracked       0.00      0.00      0.00      4000

    accuracy                           0.50      8000
   macro avg       0.25      0.50      0.33      8000
weighted avg       0.25      0.50      0.33      8000

Почему у моей матрицы путаницы 0?