Keras Image Augmentation Code Of Image
Croptoaspectratio: If True, resize the images without aspect ratio distortion. Import numpy as np import pandas as pd from sklearn.modelselection import traintestsplit from keras.models import Model from keras.layers import Conv2D, MaxPooling2D, GlobalMaxPooling2D from keras. This Notebook has been released under the Apache 2.0 open source license. Keras ResNet with image augmentation Kaggle. Shearrange, zoomrange, and horizontalflip. You can also refer this Keras’ ImageDataGenerator tutorial which has explained how this ImageDataGenerator class work.The following is example code of image augmentation here, the ImageDataGenerator class is used for processing.
Each class contain 50 images. You can download the dataset here and save & unzip it in your current working directory. Prepare DatasetFor demonstration, we use the fruit dataset which has two types of fruit such as banana and Apricot. These three functions are:Each of these function is achieving the same task to loads the image dataset in memory and generates batches of augmented data, but the way to accomplish the task is different.This tutorial has explained flow() function with example.
In :Img = cv2.imread(os.path.join(src_path,e))Let’s normalized each pixel values to the range and encode the target label. In :From keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, DropoutFrom keras.preprocessing.image import ImageDataGeneratorFrom sklearn.preprocessing import LabelEncoderFrom sklearn.model_selection import train_test_splitLet’s load the train images and test images. In :Path = os.path.join(src_path,sub_class)Img = plt.imread(os.path.join(path,str(i)+'.jpg'))Plt.imshow(img, cmap=plt.get_cmap('gray'))Let’s import the required packages.
In :Model.add(Conv2D(32,kernel_size=(3,3),activation='relu',input_shape=(100, 100, 3)))Model.add(MaxPooling2D(pool_size=(2, 2)))Model.add(Dense(1, activation='sigmoid'))Model.compile(loss="binary_crossentropy",optimizer="adam",metrics=)Model.fit_generator(train_aug, validation_data=(testX, testY),Steps_per_epoch=len(trainX) // batch_size,10/10 - 2s 182ms/step - loss: 0.7499 - acc: 0.5875 - val_loss: 0.3824 - val_acc: 0.712510/10 - 1s 130ms/step - loss: 0.3015 - acc: 0.7500 - val_loss: 0.2117 - val_acc: 0.762510/10 - 1s 127ms/step - loss: 0.2017 - acc: 0.8250 - val_loss: 0.1759 - val_acc: 0.981210/10 - 1s 125ms/step - loss: 0.1159 - acc: 1.0000 - val_loss: 0.0284 - val_acc: 1.000010/10 - 1s 132ms/step - loss: 0.0109 - acc: 1.0000 - val_loss: 0.0062 - val_acc: 1.0000Score = model.evaluate_generator(valid_generator)Let’s make a prediction on test data using Keras’ predict_generator: In :Predict = model.
0 kommentar(er)
