Your Web News in One Place

An Interest In:

Web News this Week

Search Archive

Some of Our Sources

View All Sources

Help Webnuz

Referal links:

Sign up for GreenGeeks web hosting
June 21, 2021 12:05 am GMT

How to prepare custom image dataset, split as train set & test set and build a CNN model using Keras?

Imagine you have two class of images, Class_A & Class_B.

Now, you need a custom dataset with train set and test set for training and validation of our image data.

We are going to use Keras for our Dataset generation.

image
----------------------------------logo:keras.io----------------------------

Steps in creating the directory for images:

  1. Create folder named data
  2. Create folders train and validation as subfolders inside folder data.
  3. Create folders class_A and class_B as subfolders inside train and validation folders.
  4. Place 80% class_A images in data/train/class_A folder path.
  5. Place 20% class_A imagess in `data/validation/class_A folder path.
  6. Place 80% class_B images in data/train/class_B folder path.
  7. Place 20% class_B imagess in data/validation/class_B folder path.

Directory structure.

`

data/    train/        class_A/            class_A001.jpg            class_A002.jpg            .            .            .        class_B/            class_B001.jpg            class_B002.jpg             .             .             .    validation/        class_A/            class_A001.jpg            class_A002.jpg             .             .             .        class_B/            class_B001.jpg            class_B002.jpg             .             .             .

Steps to do in code.

1, Imports.

from keras.preprocessing.image import ImageDataGeneratorfrom keras.models import Sequentialfrom keras.layers import Conv2D, MaxPooling2Dfrom keras.layers import Activation, Dropout, Flatten, Dense

2, Initialize variables as follow

# image dimensions, set as per your preference.img_width, img_height = 150, 150train_data_dir = 'data/train'validation_data_dir = 'data/validation'# set the following parameters as per your preferencebatch_size = 10nb_train_samples = 800nb_validation_samples = 200epochs = 40

3, Augmentation configuration for train set

train_datagen = ImageDataGenerator(    rescale=1. / 255,    shear_range=0.2,    zoom_range=0.2,    horizontal_flip=True)

4, Augmentation configuration for test set

# rescalingtest_datagen = ImageDataGenerator(rescale=1. / 255)

5, Now, use the flow_from_directory() method in ImageDataGenerator class to generate a tf.data.Dataset from image files in a directory.

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')

6, Build an image classifier model, a sequential CNN architecture with relu as hidden neurons activation function and sigmoid as output neuron activation function.

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'))

7, Compile the model as follows

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

8, Now use fit() method to fit your train set and validate your image dataset and calculate steps_per_epoch & validation_steps by doing a floor division of steps_per_epoch=nb_train_samples // batch_size validation_steps=nb_validation_samples // batch_size.

model.fit(    train_generator,    steps_per_epoch=nb_train_samples // batch_size,    epochs=epochs,    validation_data=validation_generator,    validation_steps=nb_validation_samples // batch_size)

Reference :

Keras Image data preprocessing

Personal Blog @ danyson.github.io


Original Link: https://dev.to/danyson/how-to-prepare-custom-image-dataset-split-as-train-set-test-set-and-build-a-cnn-model-using-keras-47jo

Share this article:    Share on Facebook
View Full Article

Dev To

An online community for sharing and discovering great ideas, having debates, and making friends

More About this Source Visit Dev To