Brightness_range Keras is an argument in ImageDataGenerator class of keras.preprocessing.image package. We can use it to adjust the brightness_range of any image for Data Augmentation. This article will explain to you the term Data Augmentation. In addition, We will also see how can we achieve Data Augmentation using brightness_range in Keras.
Data Augmentation with brightness_range –
Firstly, let’s understand the term Data Augmentation. Well! when you have less data for training or you want to add more variety of data in the dataset. You may generate more data by cropping, adding brightness, padding of existing data(Image). This technique is Data Argumentation in image processing.
As I have already mentioned that increasing and decreasing the brightness of the image. Also comes into the data Argumentation in Image processing.
Brightness_range TensorFlow Syntax-
Here is the syntax for the brightness_range argument in Tensorflow API. Basically, TensorFlow 2.0 is having a similar syntax to Keras under its package tensorflow.keras.
from tensorflow.keras.preprocessing.image import ImageDataGenerator imageDataGenerator_obj= ImageDataGenerator(brightness_range=(0.2, 0.8))
Here the range starts from zero which signifies no brightness of the image. Also, the upper range is 1 which signifies the maximum range of the brightness.
Brightness_range Keras Syntax –
Let’s see the implementation of brightness_range in core Keras API.
from keras.preprocessing.image import ImageDataGenerator datagen = ImageDataGenerator(brightness_range=[0.2,1.0])
There is a big difference in the parameter of Tensorflow brightness_range with this API. In Keras, 1.0 is the neutral brightness. If you go down to 1 it will start darkening the image. And if you go above to 1 ( value) it will start brightening the image.
In the above syntax example, We have used the brightness_range=[0.2,1.0]. This will darken the image in this range.
Step by step Implementation of brightness_range Keras –
Let’s implement the data argumentation with it.
Import the relevant packages.
from numpy import expand_dims from keras.preprocessing.image import load_img from keras.preprocessing.image import img_to_array from keras.preprocessing.image import ImageDataGenerator from matplotlib import pyplot from io import BytesIO from PIL import Image
Image loading and conversion into the array. I am working over google colab. Hence please change the code if you are doing it locally.
#specific to Google Colab only from google.colab import files uploaded = files.upload() #Loading the image and converting into Byte img_array= Image.open(BytesIO(uploaded["lamborghini_660_140220101539.jpg"]))
For instance, we have taken the sample image
"lamborghini_660_140220101539.jpg", you may change at your convenience.
Data argumentation for the above image.
# dimesion adjustment sam = expand_dims(img_array, 0) # create image data augmentation generator imageDataGenerator_obj = ImageDataGenerator(brightness_range=[0.3,0.9])
Now we will plot the image.
iterator = imageDataGenerator_obj.flow(sam, batch_size=1) for j in range(6): pyplot.subplot(330 + 1 + j) chunk = iterator.next() sub_img = chunk.astype('uint8') pyplot.imshow(sub_img) pyplot.show()
Full code with output-
Above all, Here is the complete code from each step.
from numpy import expand_dims from keras.preprocessing.image import load_img from keras.preprocessing.image import img_to_array from keras.preprocessing.image import ImageDataGenerator from matplotlib import pyplot from io import BytesIO from PIL import Image #Loading the image and coverting into Byte img_array= Image.open(BytesIO(uploaded["lamborghini_660_140220101539.jpg"])) # dimesion adjustment sam = expand_dims(img_array, 0) # create image data augmentation generator imageDataGenerator_obj = ImageDataGenerator(brightness_range=[0.3,0.9]) # image ploting iterator = imageDataGenerator_obj.flow(sam, batch_size=1) for j in range(6): pyplot.subplot(330 + 1 + j) chunk = iterator.next() sub_img = chunk.astype('uint8') pyplot.imshow(sub_img) pyplot.show()
After that, Let’s see the output for the full code.
Above all, As you can see, We have generated the six different images from a single one. Just by changing the brightness. data argumentation also helps to stop overfitting the model.
Data Science Learner Team
These are the question asked on the Keras by the data science reader.
Q: I am getting No module named keras Import error. How to fix it?
This error comes where you have not install Keras module and importing it. It can be solved if you install it. To install you can use the pip command.
pip install Keras
There is a dedicated step-by-step fix to remove No module named keras error.
Q 2: How to install TensorFlow in PyCharm
Kera requires TensorFlow to be installed in your system. So before implementing deep learning you have to install TensorFlow. You can install tensorflow using the pip command.
pip install --upgrade tensorflow
It will install TensorFlow on your system. There is a dedicated tutorial on how to install TensorFlow in pycharm. Please read it to know more.
Join our list
Subscribe to our mailing list and get interesting stuff and updates to your email inbox.