confusion matrix and F1 score for an image classifier

Question

hiya i followed this guide on how to make a powerfull image classifier with little data from https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html I need help on making a cofusion matrix and getting the F1 score of this code this is an image classifier that detects tumor the datasets are all grayscaled

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
from PIL import ImageFile, Image
print(Image.__file__)
import numpy as np
import matplotlib.pyplot as plt

# dimensions of our images.
img_width, img_height = 150, 150

train_data_dir = r'C:\Users\Acer\imagerec\Brain\TRAIN'
validation_data_dir = r'C:\Users\Acer\imagerec\Brain\VAL'
nb_train_samples = 140
nb_validation_samples = 40
epochs = 20
batch_size = 5

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

from keras.applications.vgg16 import VGG16
from keras.models import Model
from keras.layers import Dense

vgg = VGG16(include_top=False, weights='imagenet', input_shape=(), pooling='avg')
x = vgg.output
x = Dense(1, activation='sigmoid')(x)
model = Model(vgg.input, x)
model.summary()

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

model.save_weights('first_try.h5')

edit now i got these codes

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
from PIL import ImageFile, Image
print(Image.__file__)
import numpy
import matplotlib.pyplot as plt

# dimensions of our images.
img_width, img_height = 150, 150

train_data_dir = r'C:\Users\Acer\imagerec\Brain\TRAIN'
validation_data_dir = r'C:\Users\Acer\imagerec\Brain\VAL'
nb_train_samples = 140
nb_validation_samples = 40
epochs = 2
batch_size = 5

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

from keras.applications.vgg16 import VGG16
from keras.models import Model
from keras.layers import Dense

vgg = VGG16(include_top=False, weights='imagenet', input_shape=(), pooling='avg')
x = vgg.output
x = Dense(1, activation='sigmoid')(x)
model = Model(vgg.input, x)
model.summary()

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

test_steps_per_epoch = numpy.math.ceil(test_datagen.samples / test_datagen.batch_size)

predictions = model.predict_generator(validation_generator, steps=test_steps_per_epoch)
# Get most likely class
predicted_classes = numpy.argmax(predictions, axis=1)
true_classes = validation_generator.classes
class_labels = list(validation_generator.class_indices.keys())
report = classification_report(true_classes, predicted_classes, target_names=class_labels)
print(report)

cm=confusion_matrix(true_classes,predicted_classes)
print(cm)

model.save_weights('first_try.h5')

solved

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
from PIL import ImageFile, Image
print(Image.__file__)
import numpy
import matplotlib.pyplot as plt

# dimensions of our images.
img_width, img_height = 150, 150

train_data_dir = r'C:\Users\Acer\imagerec\Brain\TRAIN'
validation_data_dir = r'C:\Users\Acer\imagerec\Brain\VAL'
nb_train_samples = 140
nb_validation_samples = 40
epochs = 2
batch_size = 5

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

from keras.applications.vgg16 import VGG16
from keras.models import Model
from keras.layers import Dense

vgg = VGG16(include_top=False, weights='imagenet', input_shape=(), pooling='avg')
x = vgg.output
x = Dense(1, activation='sigmoid')(x)
model = Model(vgg.input, x)
model.summary()

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

test_steps_per_epoch = numpy.math.ceil(validation_generator.samples / validation_generator.batch_size)

predictions = model.predict_generator(validation_generator, steps=test_steps_per_epoch)
# Get most likely class
predicted_classes = numpy.argmax(predictions, axis=1)
true_classes = validation_generator.classes
class_labels = list(validation_generator.class_indices.keys())
report = classification_report(true_classes, predicted_classes, target_names=class_labels)
print(report)

cm=confusion_matrix(true_classes,predicted_classes)
print(cm)

plt.imshow(cm)


model.save_weights('first_try.h5')

Answer 1

The below code would do a confusion matrix and classification report for your validation generator

from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

predictions = model.predict_generator(validation_generator, steps=test_steps_per_epoch)
test_steps_per_epoch = numpy.math.ceil(validation_generator.samples / validation_generator.batch_size)
predicted_classes = numpy.argmax(predictions, axis=1)
true_classes = validation_generator.classes
class_labels = list(validation_generator.class_indices.keys())
report = classification_report(true_classes, predicted_classes, target_names=class_labels)
print(report)   

cm=confusion_matrix(true_classes,predicted_classes)
print(cm)

to plot use

import matplotlib.pyplot as plt
plt.imshow(cm)