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.

Practice

1. What is the main purpose of using data transforms in PyTorch?

easy

A. To prepare and modify raw data before feeding it to a model

B. To create new neural network layers

C. To evaluate model accuracy

D. To save the trained model to disk

Solution

1. Step 1: Understand the role of data transforms

   Data transforms modify raw data to make it suitable for model input, such as resizing or normalizing images.

2. Step 2: Differentiate from other tasks

   Creating layers, evaluating accuracy, or saving models are separate tasks unrelated to data transforms.

3. Final Answer:

   To prepare and modify raw data before feeding it to a model -> Option A

4. Quick Check:

   Data transforms = prepare data [OK]

Hint: Transforms prepare data, not model or evaluation tasks [OK]

Common Mistakes:

• Confusing transforms with model building
• Thinking transforms evaluate model performance
• Mixing transforms with saving models

2. Which of the following is the correct way to chain multiple transforms using PyTorch's torchvision?

easy

A. transforms.Sequence(transforms.Resize(256), transforms.ToTensor())

B. transforms.Chain([transforms.Resize(256), transforms.ToTensor()])

C. transforms.Pipeline(transforms.Resize(256), transforms.ToTensor())

D. transforms.Compose([transforms.Resize(256), transforms.ToTensor()])

Solution

1. Step 1: Recall the correct class for chaining transforms

   PyTorch uses transforms.Compose to chain multiple transforms in a list.

2. Step 2: Check syntax correctness

   Only transforms.Compose accepts a list of transforms; others like Sequence, Pipeline, Chain do not exist in torchvision.

3. Final Answer:

   transforms.Compose([transforms.Resize(256), transforms.ToTensor()]) -> Option D

4. Quick Check:

   Use Compose for chaining transforms [OK]

Hint: Remember Compose takes a list of transforms [OK]

Common Mistakes:

• Using non-existent classes like Sequence or Pipeline
• Passing transforms as separate arguments instead of a list
• Confusing Compose with other transform functions

3. What will be the output shape of the tensor after applying the following transform to a 3-channel image of size 100x100?
transform = transforms.Compose([transforms.Resize(50), transforms.ToTensor()])

medium

A. [1, 50, 50]

B. [50, 50, 3]

C. [3, 50, 50]

D. [50, 3, 50]

Solution

1. Step 1: Understand Resize effect

   transforms.Resize(50) resizes the image to 50x50 pixels, keeping the number of channels unchanged (3 channels).

2. Step 2: Understand ToTensor output shape

   transforms.ToTensor() converts the image to a tensor with shape [channels, height, width], so shape is [3, 50, 50].

3. Final Answer:

   [3, 50, 50] -> Option C

4. Quick Check:

   Tensor shape = [channels, height, width] [OK]

Hint: Tensor shape is channels first after ToTensor [OK]

Common Mistakes:

• Assuming channels last format
• Confusing Resize parameter as channels
• Mixing height and width order

4. Identify the error in this transform code snippet:

transform = transforms.Compose([
    transforms.Resize(128),
    transforms.Normalize(mean=[0.5], std=[0.5]),
    transforms.ToTensor()
])

medium

A. ToTensor should be first

B. Normalize should come after ToTensor

C. Resize must be after Normalize

D. No error, code is correct

Solution

1. Step 1: Check order of transforms

   transforms.Normalize expects a tensor input, but here it is before ToTensor, which converts image to tensor.

2. Step 2: Correct order

   ToTensor must come before Normalize to convert image to tensor first, then normalize it.

3. Final Answer:

   Normalize should come after ToTensor -> Option B

4. Quick Check:

   Normalize after ToTensor [OK]

Hint: Normalize needs tensor input, so place after ToTensor [OK]

Common Mistakes:

• Placing Normalize before ToTensor
• Assuming Resize order matters with Normalize
• Thinking ToTensor can be anywhere

5. You want to apply random horizontal flip and then normalize an image tensor. Which of the following transform sequences is correct to ensure proper data augmentation and normalization?

hard

A. transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5])])

B. transforms.Compose([transforms.ToTensor(), transforms.RandomHorizontalFlip(), transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5])])

C. transforms.Compose([transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5]), transforms.RandomHorizontalFlip(), transforms.ToTensor()])

D. transforms.Compose([transforms.RandomHorizontalFlip(), transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5]), transforms.ToTensor()])

Solution

1. Step 1: Understand transform order for augmentation and normalization

   RandomHorizontalFlip works on PIL images, so it must come before ToTensor.

2. Step 2: Normalize after converting to tensor

   Normalize requires tensor input, so it must come after ToTensor.

3. Final Answer:

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5])]) -> Option A

4. Quick Check:

   Flip before ToTensor, Normalize after ToTensor [OK]

Hint: Augment on images, normalize on tensors [OK]

Common Mistakes:

• Applying Normalize before ToTensor
• Applying RandomHorizontalFlip after ToTensor
• Mixing order of augmentation and normalization