How to predict input image using trained model in Keras?

Question

I trained a model to classify images from 2 classes and saved it using model.save(). Here is the code I used:

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


# dimensions of our images.
img_width, img_height = 320, 240

train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 200  #total
nb_validation_samples = 10  # total
epochs = 6
batch_size = 10

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

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

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=5)

model.save('model.h5')

It successfully trained with 0.98 accuracy which is pretty good. To load and test this model on new images, I used the below code:

from keras.models import load_model
import cv2
import numpy as np

model = load_model('model.h5')

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

img = cv2.imread('test.jpg')
img = cv2.resize(img,(320,240))
img = np.reshape(img,[1,320,240,3])

classes = model.predict_classes(img)

print classes

It outputs:

[[0]]

Why wouldn't it give out the actual name of the class and why [[0]]?

Answer 1

keras predict_classes (docs) outputs A numpy array of class predictions. Which in your model case, the index of neuron of highest activation from your last(softmax) layer. [[0]] means that your model predicted that your test data is class 0. (usually you will be passing multiple image, and the result will look like [[0], [1], [1], [0]] )

You must convert your actual label (e.g. 'cancer', 'not cancer') into binary encoding (0 for 'cancer', 1 for 'not cancer') for binary classification. Then you will interpret your sequence output of [[0]] as having class label 'cancer'