Feature extraction approach in TensorFlow - Model Pipeline Trace

Model Pipeline - Feature extraction approach

This pipeline shows how we use a pre-trained model to extract important features from images. These features help a smaller model learn faster and better for a new task.

Data Flow - 5 Stages

1Input images

1000 rows x 224 x 224 x 3→Raw images loaded for processing→1000 rows x 224 x 224 x 3

Image of a cat with 224x224 pixels and 3 color channels

↓

2Preprocessing

1000 rows x 224 x 224 x 3→Normalize pixel values to range 0-1→1000 rows x 224 x 224 x 3

Pixel value 120 becomes 0.47

↓

3Feature extraction

1000 rows x 224 x 224 x 3→Pass images through pre-trained CNN (e.g., MobileNetV2) without top layers→1000 rows x 7 x 7 x 1280

Image features represented as 7x7 grid with 1280 channels

↓

4Global average pooling

1000 rows x 7 x 7 x 1280→Convert feature maps to 1D feature vector per image→1000 rows x 1280

Feature vector like [0.12, 0.05, ..., 0.33]

↓

5Classifier training

1000 rows x 1280→Train a small dense layer to classify images using extracted features→1000 rows x 10

Output probabilities for 10 classes like [0.1, 0.05, ..., 0.2]

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	0.45	Model starts learning with moderate loss and accuracy
2	1.20	0.65	Loss decreases and accuracy improves as model learns features
3	0.85	0.75	Training continues with better performance
4	0.65	0.82	Model converges with lower loss and higher accuracy
5	0.50	0.87	Final epoch shows good accuracy and stable loss

Prediction Trace - 4 Layers

Layer 1: Input image

Layer 2: Feature extractor (MobileNetV2)

Layer 3: Global average pooling

Layer 4: Dense classifier layer

Model Quiz - 3 Questions

What is the shape of the data after feature extraction?

A 1000 rows x 224 x 224 x 3

B 1000 rows x 7 x 7 x 1280

C 1000 rows x 1280

D 1000 rows x 10

Key Insight

Using a pre-trained model to extract features helps the new model learn faster and better by focusing on important image details instead of raw pixels.