Data transforms in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a data transform in PyTorch?

A data transform is a function or operation applied to data samples to change or prepare them before feeding into a model. It can include resizing images, normalizing values, or converting data types.

beginner

Why do we normalize images in data transforms?

Normalization scales image pixel values to a standard range, often zero mean and unit variance. This helps the model learn better and faster by keeping input values consistent.

intermediate

How does the Compose transform work in PyTorch?

Compose chains multiple transforms together. It applies each transform in order to the data sample, making it easy to combine steps like resizing, cropping, and normalizing.

beginner

What is the purpose of ToTensor transform?

ToTensor converts images or data from PIL Image or numpy arrays into PyTorch tensors. It also scales pixel values from 0-255 integers to 0-1 floats.

intermediate

Give an example of a common data transform pipeline for image classification.

A typical pipeline: Resize image to fixed size, convert to tensor, normalize with mean and std. For example: Compose([Resize(256), CenterCrop(224), ToTensor(), Normalize(mean, std)]).

What does the Normalize transform do in PyTorch?

A Randomly flips images horizontally

B Converts images to tensors

C Resizes images to a fixed size

D Scales data to zero mean and unit variance

Normalize adjusts data values to have a mean of zero and a standard deviation of one, helping model training.

Which transform converts a PIL image to a PyTorch tensor?

A Resize

B ToTensor

C Normalize

D RandomCrop

ToTensor converts images from PIL or numpy format into PyTorch tensors.

What is the main use of Compose in data transforms?

A To chain multiple transforms together

B To normalize images

C To convert data to tensors

D To load datasets

Compose allows applying several transforms in sequence to data samples.

Why do we resize images in data transforms?

A To make all images the same size for the model

B To convert images to grayscale

C To increase image brightness

D To shuffle image pixels

Models require inputs of fixed size, so resizing ensures consistency.

Which transform would you use to randomly flip images horizontally?

A CenterCrop

B Normalize

C RandomHorizontalFlip

D ToTensor

RandomHorizontalFlip randomly flips images left to right to augment data.

Explain the role of data transforms in preparing images for a PyTorch model.

Think about steps to make images ready and consistent for training.

Describe how you would create a data transform pipeline for training an image classifier.

Consider both preparing and augmenting images.