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.