How to apply normalization to images in testing phase when using keras ImageDataGenerator?

Question

I'm trying to predict a new image using trained model. My accuracy is 95%. But the predict_classes always return the first label [0] whatever I input. I guess one of the reason is I use featurewise_center=True and samplewise_center=True in ImageDataGenerator. I think I should do the same thing on my input image. But I can't find what did these function do to the image.

Any suggestion will be appreciated.

ImageDataGenerator code:

train_datagen = ImageDataGenerator(
samplewise_center=True,
rescale=1. / 255,
shear_range=30,
zoom_range=30,
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2)

test_datagen = ImageDataGenerator(
samplewise_center=True,
rescale=1. / 255,
shear_range=30,
zoom_range=30,
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=True)

Prediction code (I use 100*100*3 image to train the model):

model = load_model('CNN_model.h5')
img = cv2.imread('train/defect/6.png')
img = cv2.resize(img,(100,100))
img = np.reshape(img,[1,100,100,3])
img = img/255.

classes = model.predict_classes(img)

print (classes)

updated 11/14:

I change my code to predict image like below. But the model still predict the same class even if I feed the image which I have used to train my model(and got 95% accuarcy). Is there anything I missed?

model = load_model('CNN_model.h5')
img = cv2.imread('train/defect/6.png')
img = cv2.resize(img,(100,100))
img = np.reshape(img,[1,100,100,3])
img = np.array(img, dtype=np.float64) 
img = train_datagen.standardize(img)

classes = model.predict_classes(img)
print(classes)

Maybe you could access the `featurewise_center` and `samplewise_center` attributes of a generator and apply them to the images? — Novak, Nov 07 '18 at 10:05

today · Answer 1 · 2018-11-07T11:40:25.053

You need to use the standardize() method of ImageDataGenerator instance. From Keras documentation:

standardize
standardize(x)
Applies the normalization configuration to a batch of inputs.

Arguments

x: Batch of inputs to be normalized.

Returns

The inputs, normalized.

So it would be like this:

img = cv2.imread('train/defect/6.png')
img = cv2.resize(img,(100,100))
img = np.reshape(img,[1,100,100,3])
img = train_datagen.standardize(img)

classes = model.predict_classes(img)

Note that it would apply the rescaling as well so there is no need to do it yourself (i.e. remove img = img/255.).

Further, keep in mind that since you have set featurewise_ceneter=True you need to use fit() method of generator before using it for training:

train_datagen.fit(training_data)

# then use fit_generator method
model.fit_generator(train_datagen, ...)

Thanks for your notice. I remove featurewise ceneter to make my code easier, but the problem still exist. I revise my code in my question. Any suggestion will be greatly appreciate. — Gamuza, Nov 14 '18 at 11:21
@Gamuza What if you predict on all of your training data? Do you get 95% accuracy? — today, Nov 14 '18 at 11:29

score 1 · Answer 2 · answered May 23 '19 at 12:56

I think it's the problem that you used cv2 to import your images, because when you use cv2.imread, the channels are not "r,g,b" but "b,g,r".

for example,

import cv2
from tensorflow.keras.preprocessing import image

bgr = cv2.imread('r.jpg')
rgb = np.array(image.load_img('r.jpg'))
print(bgr[1,1,:],rgb[1,1,:])

result:

[ 83 113   0] [  0 114  83]

score 0 · Answer 3 · answered Feb 04 '19 at 08:45

Not a complete answer but some information:

From this link that is referenced in keras docs:

# 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')

I think you should do this way for training. Then for test I think using train_datagen.standardize is true.

How to apply normalization to images in testing phase when using keras ImageDataGenerator?

3 Answers3

standardize

Linked