How can I add zero-padding to make images in dataset of equal size?

Question

I'm working with a dataset having a size of more than 30Gb, the problem is that the images(RGB) in the dataset aren't of the same dimension. As I'm implementing custom CNN I'll be required to give input_size for the first convolutional layer. Is there any way to add zero-padding generically. I've initially implemented a pre-trained model(ResNet-50) and used the following method

from tensorflow.keras.applications.resnet50 import preprocess_input 
ImageDataGenerator(preprocess_input ,validation_split=0.2)

This made my dataset compatible with the model, is there any similar way where I can add zero-padding on the dataset but for a custom CNN model.

score 0 · Answer 1 · answered Jan 09 '21 at 04:47

0

Although zero-padding might not be an ideal solution for handling images of various sizes, you can zero-pad images in python by the following methods.

Numpy method reference

padded_image = np.zeros(result_shape)
padded_image[:image.shape[0],:image.shape[1]] = image

Tensorflow method documentation

padded_image = tf.image.pad_to_bounding_box(image, top_padding, left_padding, target_height, target_width)

answered Jan 09 '21 at 04:47

krenerd

741
4
22

can I use images as it is? or I need to perform some pre-processing on the dataset to make it work? – Ali Sehran Jan 10 '21 at 15:37
@None Use images as it is. More arguments and explanations are described in the documentation. – krenerd Jan 11 '21 at 03:00

How can I add zero-padding to make images in dataset of equal size?

1 Answers1