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.
This question is related to
python
machine-learning
keras
computer-vision
That's because you're getting the numeric value associated with the class. For example if you have two classes cats and dogs, Keras will associate them numeric values 0 and 1. To get the mapping between your classes and their associated numeric value, you can use
>>> classes = train_generator.class_indices
>>> print(classes)
{'cats': 0, 'dogs': 1}
Now you know the mapping between your classes and indices. So now what you can do is
if classes[0][0] == 1:
prediction = 'dog'
else:
prediction = 'cat'
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]
Forwarding the example by @ritiek, I'm a beginner in ML too, maybe this kind of formatting will help see the name instead of just class number.
images = np.vstack([x, y])
prediction = model.predict(images)
print(prediction)
i = 1
for things in prediction:
if(things == 0):
print('%d.It is cancer'%(i))
else:
print('%d.Not cancer'%(i))
i = i + 1
You can use model.predict()
to predict the class of a single image as follows [doc]:
# load_model_sample.py
from keras.models import load_model
from keras.preprocessing import image
import matplotlib.pyplot as plt
import numpy as np
import os
def load_image(img_path, show=False):
img = image.load_img(img_path, target_size=(150, 150))
img_tensor = image.img_to_array(img) # (height, width, channels)
img_tensor = np.expand_dims(img_tensor, axis=0) # (1, height, width, channels), add a dimension because the model expects this shape: (batch_size, height, width, channels)
img_tensor /= 255. # imshow expects values in the range [0, 1]
if show:
plt.imshow(img_tensor[0])
plt.axis('off')
plt.show()
return img_tensor
if __name__ == "__main__":
# load model
model = load_model("model_aug.h5")
# image path
img_path = '/media/data/dogscats/test1/3867.jpg' # dog
#img_path = '/media/data/dogscats/test1/19.jpg' # cat
# load a single image
new_image = load_image(img_path)
# check prediction
pred = model.predict(new_image)
In this example, a image is loaded as a numpy
array with shape (1, height, width, channels)
. Then, we load it into the model and predict its class, returned as a real value in the range [0, 1] (binary classification in this example).
Source: Stackoverflow.com