Data transforms in PyTorch - Model Pipeline Trace

Model Pipeline - Data transforms

This pipeline shows how raw data is changed step-by-step to prepare it for a machine learning model. We clean, resize, and convert images into numbers the model can understand.

Data Flow - 4 Stages

1Raw Data Input

1000 images x 3 channels x 256 height x 256 width→Load images from disk in RGB format→1000 images x 3 channels x 256 height x 256 width

Image of a cat with shape (3, 256, 256)

↓

2Resize

1000 images x 3 channels x 256 height x 256 width→Resize images to 128x128 pixels→1000 images x 3 channels x 128 height x 128 width

Resized cat image with shape (3, 128, 128)

↓

3ToTensor

1000 images x 3 channels x 128 height x 128 width (PIL images)→Convert images to PyTorch tensors and scale pixel values to [0,1]→1000 tensors x 3 channels x 128 height x 128 width (float32)

Tensor with values between 0 and 1 representing the cat image

↓

4Normalize

1000 tensors x 3 channels x 128 height x 128 width→Subtract mean and divide by std for each channel→1000 normalized tensors x 3 channels x 128 height x 128 width

Tensor with mean 0 and std 1 per channel for the cat image

Training Trace - Epoch by Epoch

Loss
1.2 |****
1.0 |*** 
0.8 |**  
0.6 |*   
0.4 |****
     1  2  3  4  5  Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning with high loss and low accuracy
2	0.9	0.60	Loss decreases and accuracy improves as model learns
3	0.7	0.72	Model continues to improve with more training
4	0.5	0.80	Loss lowers further and accuracy reaches 80%
5	0.4	0.85	Training converges with good accuracy and low loss

Prediction Trace - 4 Layers

Layer 1: Input Image

Layer 2: Resize

Layer 3: ToTensor

Layer 4: Normalize

Model Quiz - 3 Questions

What does the 'Normalize' step do to the image data?

A Changes pixel values to have zero mean and unit variance

B Resizes the image to smaller dimensions

C Converts image to grayscale

D Loads the image from disk

Key Insight

Data transforms prepare raw images into a clean, consistent format that helps the model learn better and faster. Normalizing data centers values, making training more stable.

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