I'm only beginning with keras and machine learning in general.
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]]
?
Thanks in advance.
If someone is still struggling to make predictions on images, here is the optimized code to load the saved model and make predictions:
# Modify 'test1.jpg' and 'test2.jpg' to the images you want to predict on
from keras.models import load_model
from keras.preprocessing import image
import numpy as np
# dimensions of our images
img_width, img_height = 320, 240
# load the model we saved
model = load_model('model.h5')
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# predicting images
img = image.load_img('test1.jpg', target_size=(img_width, img_height))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
images = np.vstack([x])
classes = model.predict_classes(images, batch_size=10)
print classes
# predicting multiple images at once
img = image.load_img('test2.jpg', target_size=(img_width, img_height))
y = image.img_to_array(img)
y = np.expand_dims(y, axis=0)
# pass the list of multiple images np.vstack()
images = np.vstack([x, y])
classes = model.predict_classes(images, batch_size=10)
# print the classes, the images belong to
print classes
print classes[0]
print classes[0][0]