nn.Conv2d layers in PyTorch - Model Pipeline Trace

Model Pipeline - nn.Conv2d layers

This pipeline shows how a convolutional neural network (CNN) uses nn.Conv2d layers to learn from images. The model extracts features from images by sliding filters over them, then learns to classify the images based on these features.

Data Flow - 6 Stages

1Input Image

1000 rows x 3 channels x 32 height x 32 width→Raw RGB images of size 32x32 pixels with 3 color channels→1000 rows x 3 channels x 32 height x 32 width

An image of a cat represented as a 3D array of pixel colors

↓

2First Conv2d Layer

1000 rows x 3 channels x 32 height x 32 width→Apply 16 filters of size 3x3 with stride 1 and padding 1→1000 rows x 16 channels x 32 height x 32 width

Feature maps highlighting edges and textures in the image

↓

3ReLU Activation

1000 rows x 16 channels x 32 height x 32 width→Apply ReLU to keep only positive activations→1000 rows x 16 channels x 32 height x 32 width

Negative values set to zero, positive values unchanged

↓

4Max Pooling

1000 rows x 16 channels x 32 height x 32 width→Downsample by taking max over 2x2 regions with stride 2→1000 rows x 16 channels x 16 height x 16 width

Reduced size feature maps focusing on strongest features

↓

5Second Conv2d Layer

1000 rows x 16 channels x 16 height x 16 width→Apply 32 filters of size 3x3 with stride 1 and padding 1→1000 rows x 32 channels x 16 height x 16 width

More complex features like shapes and patterns extracted

↓

6Flatten and Fully Connected Layer

1000 rows x 32 channels x 16 height x 16 width→Flatten to 1000 rows x 8192 features, then fully connected to 10 outputs→1000 rows x 10 classes

Class scores for 10 categories like dog, cat, car, etc.

Training Trace - Epoch by Epoch

Loss
2.0 |****
1.5 |*** 
1.0 |**  
0.5 |*   
0.0 +----
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.85	0.35	Model starts learning, loss high, accuracy low
2	1.20	0.55	Loss decreases, accuracy improves as features learned
3	0.85	0.70	Model captures important patterns, accuracy rises
4	0.65	0.78	Loss continues to drop, model generalizes better
5	0.50	0.83	Training converges with good accuracy

Prediction Trace - 6 Layers

Layer 1: Input Image

Layer 2: First Conv2d Layer

Layer 3: ReLU Activation

Layer 4: Max Pooling

Layer 5: Second Conv2d Layer

Layer 6: Flatten and Fully Connected Layer

Model Quiz - 3 Questions

What does the first Conv2d layer do to the input image?

A Extracts simple features like edges using filters

B Reduces image size by half

C Converts image to grayscale

D Flattens image into a vector

Key Insight

Convolutional layers slide filters over images to extract features like edges and shapes. Activation functions like ReLU keep only useful signals. Pooling layers reduce spatial size to focus on important features and reduce computation. Together, these layers help the model learn to recognize patterns in images effectively.