Data augmentation in PyTorch - Model Pipeline Trace

Model Pipeline - Data augmentation

Data augmentation is a technique to create more training data by making small changes to existing images. This helps the model learn better by seeing many versions of the same image.

Data Flow - 4 Stages

1Original dataset

1000 images x 3 channels x 32 height x 32 width→Load raw images→1000 images x 3 x 32 x 32

Image of a cat with RGB channels

↓

2Apply random horizontal flip

1000 images x 3 x 32 x 32→Flip images horizontally with 50% chance→1000 images x 3 x 32 x 32

Cat image flipped left to right

↓

3Apply random rotation

1000 images x 3 x 32 x 32→Rotate images randomly between -15 and 15 degrees→1000 images x 3 x 32 x 32

Cat image rotated slightly clockwise

↓

4Normalize images

1000 images x 3 x 32 x 32→Scale pixel values to mean=0.5 and std=0.5→1000 images x 3 x 32 x 32

Pixel values adjusted to range around zero

Training Trace - Epoch by Epoch

Loss
1.2 |****
0.9 |***
0.7 |**
0.55|*
0.45| 
    +------------
    Epochs 1 to 5

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 augmented data
4	0.55	0.80	Loss lowers and accuracy rises steadily
5	0.45	0.85	Model shows good learning progress with augmentation

Prediction Trace - 5 Layers

Layer 1: Input image

Layer 2: Random horizontal flip

Layer 3: Random rotation

Layer 4: Normalization

Layer 5: Model prediction

Model Quiz - 3 Questions

Why do we apply random horizontal flip during data augmentation?

A To convert images to grayscale

B To help the model learn from different views of the same image

C To reduce the image size

D To increase the number of image channels

Key Insight

Data augmentation creates varied versions of images, helping the model learn more robust features and improving accuracy by reducing overfitting.