Data transforms in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply a random horizontal flip to an image tensor using PyTorch transforms.

PyTorch

transform = torchvision.transforms.RandomHorizontalFlip(p=[1])

Drag options to blanks, or click blank then click option'

A0

B1.0

C0.5

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1.0 flips every image, which might be too much.

Using 0 means no flip happens.

The probability parameter p in RandomHorizontalFlip controls how often the flip happens. 0.5 means the image flips half the time.

2fill in blank

medium

Complete the code to convert a PIL image to a tensor using PyTorch transforms.

PyTorch

transform = torchvision.transforms.Compose([torchvision.transforms.ToTensor(), torchvision.transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5])])
image_tensor = transform([1])

Drag options to blanks, or click blank then click option'

Aimage_pil

Bimage_path

Cimage_tensor

Dimage_array

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a file path string instead of an image object.

Passing an already converted tensor.

The ToTensor() transform expects a PIL Image or numpy array as input. Here, image_pil is the correct input.

3fill in blank

hard

Fix the error in the code to resize an image to 128x128 pixels using PyTorch transforms.

PyTorch

transform = torchvision.transforms.Resize([1])

Drag options to blanks, or click blank then click option'

A128

B128, 128

C[128, 128]

D(128, 128)

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a list instead of a tuple.

Passing two separate integers without parentheses.

The Resize transform expects a size as an int or a tuple. To resize to width and height, use a tuple like (128, 128).

4fill in blank

hard

Fill both blanks to create a transform that converts an image to grayscale and then to a tensor.

PyTorch

transform = torchvision.transforms.Compose([torchvision.transforms.[1](), torchvision.transforms.[2]()])

Drag options to blanks, or click blank then click option'

AGrayscale

BToTensor

CResize

DNormalize

Attempts:

3 left

💡 Hint

Common Mistakes

Using Resize or Normalize instead of Grayscale.

Switching the order of transforms.

The Grayscale() transform converts the image to grayscale. Then ToTensor() converts it to a tensor.

5fill in blank

hard

Fill all three blanks to create a transform pipeline that resizes an image to 64x64, converts it to a tensor, and normalizes it with mean 0.5 and std 0.5.

PyTorch

transform = torchvision.transforms.Compose([
    torchvision.transforms.[1]([2]),
    torchvision.transforms.[3](),
    torchvision.transforms.Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5])
])

Drag options to blanks, or click blank then click option'

AResize

B(64, 64)

CToTensor

DGrayscale

Attempts:

3 left

💡 Hint

Common Mistakes

Using Grayscale instead of ToTensor.

Passing size as a single integer instead of a tuple.

First, Resize((64, 64)) resizes the image. Then ToTensor() converts it to a tensor. Finally, Normalize adjusts the values.

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