Built-in datasets (torchvision.datasets) in PyTorch - Model Pipeline Trace

Model Pipeline - Built-in datasets (torchvision.datasets)

This pipeline shows how to use a built-in dataset from torchvision.datasets to train a simple image classifier. It loads data, processes images, trains a model, and evaluates accuracy.

Data Flow - 5 Stages

1Load Dataset

N/A→Download and load CIFAR10 dataset with 60000 images of size 32x32x3→60000 images x 32 x 32 x 3

Image of a small airplane with RGB channels

↓

2Preprocessing

60000 images x 32 x 32 x 3→Convert images to tensors and normalize pixel values to mean=0.5, std=0.5→60000 images x 3 x 32 x 32 (tensor format)

Tensor with values roughly between -1 and 1

↓

3Train/Test Split

60000 images x 3 x 32 x 32→Split into 50000 training and 10000 test images→Train: 50000 x 3 x 32 x 32, Test: 10000 x 3 x 32 x 32

Training batch of 64 images

↓

4Model Training

Batch of 64 images x 3 x 32 x 32→Train a simple CNN classifier for 5 epochs→Model weights updated, loss decreases

Batch loss starts around 2.0 and decreases

↓

5Evaluation

Test set 10000 images x 3 x 32 x 32→Model predicts labels, compute accuracy→Accuracy score between 0 and 1

Final accuracy around 0.65 (65%)

Training Trace - Epoch by Epoch

Loss
2.0 |****
1.8 |****
1.6 |*** 
1.4 |*** 
1.2 |**  
1.0 |**  
0.8 |*   
    +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.85	0.35	Model starts learning, loss high, accuracy low
2	1.45	0.48	Loss decreases, accuracy improves
3	1.20	0.57	Model continues to learn patterns
4	1.05	0.62	Loss steadily decreases, accuracy rises
5	0.95	0.65	Training converges with good accuracy

Prediction Trace - 5 Layers

Layer 1: Input Image Tensor

Layer 2: Convolutional Layer 1

Layer 3: Max Pooling Layer

Layer 4: Fully Connected Layer

Layer 5: Softmax Activation

Model Quiz - 3 Questions

What is the shape of the dataset images after loading from torchvision.datasets?

A 50000 images x 3 x 32 x 32

B 60000 images x 32 x 32 x 3

C 60000 images x 3 x 32 x 32

D 10000 images x 32 x 32 x 3

Key Insight

Using torchvision.datasets makes it easy to load standard image datasets. Normalizing images and training a simple CNN helps the model learn useful features, shown by decreasing loss and increasing accuracy over epochs.