Image data generator parameters

[AriChow]

Hi, First of all, I would like to commend you on building a great toolbox for deep learning. I am using the Image data generator in my code as follows:

datagen = ImageDataGenerator( featurewise_center=True, # set input mean to 0 over the dataset samplewise_center=True, # set each sample mean to 0 featurewise_std_normalization=True, # divide inputs by std of the dataset samplewise_std_normalization=True, # divide each input by its std zca_whitening=False, # apply ZCA whitening rotation_range=20, # randomly rotate images in the range (degrees, 0 to 180) width_shift_range=0.2, # randomly shift images horizontally (fraction of total width) height_shift_range=0.2, # randomly shift images vertically (fraction of total height) horizontal_flip=True, # randomly flip images vertical_flip=False) # randomly flip images

Xsample,=load_data(batch_size=300,names_file=image_files,labels_file=image_labels,stain_number=stain_no)

datagen.fit(X_sample)

After training the model using image augmentation, I would like to extract the hidden representations of the model on the training and testing data.

However, I understand that I would have to do the transformations included in the data generator like feature wise_centre and sample wise_center.

Is there a way to access the parameters of the data generator to transform the images or would I have to do them manually? Thanks again, Aritra

[fchollet]

Sure, they are class attributes and you can access them. You can just check out the code for details.