CNN loading model does not work with test dataset - python-3.x

Question

I have built a CNN classifier using Keras, where:
Training dataset: 3194
Validation dataset: 1020
Test Dataset: 1023
I used the below code to build and evaluate the classifier, using training and validation datasets.
from keras.models import Sequential
from keras.layers import Conv2D,Activation,MaxPooling2D,Dense,Flatten,Dropout
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from IPython.display import display
import matplotlib.pyplot as plt
from PIL import Image
from sklearn.metrics import classification_report, confusion_matrix
import keras
from keras.layers import BatchNormalization
from keras.optimizers import Adam
classifier = Sequential()
classifier.add(Conv2D(16,(3,3),input_shape=(200,200,3)))
classifier.add(Activation('relu'))
classifier.add(Flatten())
classifier.add(Dense(128))
classifier.add(Activation('relu'))
classifier.add(Dropout(0.5))
classifier.add(Dense(2))
classifier.add(Activation('softmax'))
classifier.summary()
classifier.compile(optimizer =keras.optimizers.Adam(lr=0.1),
loss ='categorical_crossentropy',
metrics =['accuracy'])
train_datagen = ImageDataGenerator(rescale =1./255,
shear_range =0.2,
zoom_range = 0.2,
horizontal_flip =True)
test_datagen = ImageDataGenerator(rescale = 1./255)
batchsize=10
training_set = train_datagen.flow_from_directory('/home/osboxes/Downloads/Downloads/Journal_Paper/Benign_Malicious/Spectrogram/Train/',
target_size=(200,200),
batch_size= batchsize,
class_mode='categorical')
test_set = test_datagen.flow_from_directory('/home/osboxes/Downloads/Downloads/Journal_Paper/Benign_Malicious/Spectrogram/Validate/',
target_size = (200,200),
batch_size = batchsize,
shuffle=False,
class_mode ='categorical')
history=classifier.fit_generator(training_set,
steps_per_epoch = 3194 // batchsize,
epochs = 100,
validation_data =test_set,
validation_steps = 1020 // batchsize)
Y_pred = classifier.predict_generator(test_set, steps= 1020 // batchsize)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(confusion_matrix(test_set.classes, y_pred))
print('Classification Report')
target_names = test_set.classes
class_labels = list(test_set.class_indices.keys())
target_names = ['Bening','Malicious']
report = classification_report(test_set.classes, y_pred, target_names=class_labels)
print(report)
# summarize history for accuracy
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.title('model accuracy 16 with dropout rl .1')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
# summarize history for loss
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss 16 with dropout rl .1')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
classifier.save('16_With_Dropout_rl_001.h5')
After saving the model, I loaded the model using below code. Also, I am trying to evaluate the model with test dataset (that has not been seen by the classifier during the building and evaluation). However, the below code gives me the error (ValueError: Found input variables with inconsistent numbers of samples: [1023, 1020]). Any ideas why?
from keras.models import Sequential
from keras.layers import Conv2D,Activation,MaxPooling2D,Dense,Flatten,Dropout
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from IPython.display import display
import matplotlib.pyplot as plt
from PIL import Image
from keras.models import load_model
from sklearn.metrics import classification_report, confusion_matrix
from keras.models import load_model
import pickle
classifier = load_model('16_With_Dropout_rl_001.h5')
batchsize=10
test_datagen = ImageDataGenerator(rescale = 1./255)
test_set = test_datagen.flow_from_directory('/home/osboxes/Downloads/Downloads/Journal_Paper/Benign_Malicious/Spectrogram/Test/',
target_size = (200,200),
batch_size = batchsize,
shuffle=False,
class_mode ='categorical')
Y_pred = classifier.predict_generator(test_set, steps= 1023 // batchsize)
y_pred = np.argmax(Y_pred, axis=1)
print('Confusion Matrix')
print(confusion_matrix(test_set.classes, y_pred))
print('Classification Report')
target_names = test_set.classes
class_labels = list(test_set.class_indices.keys())
target_names = ['Bening', 'Malicious']
report = classification_report(test_set.classes, y_pred, target_names=class_labels)
print(report)

Answer 1

This is because of the number of steps in predict_generator(); 1023//10 yields 102 batches; Each batch of size 10 yields 1020 samples;
Thus, you have to change the line to :
Y_pred = classifier.predict_generator(test_set, steps= (1023 // batchsize)+1)