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.

Practice

1. What is the main purpose of using feature extraction with a pre-trained TensorFlow model?

easy

A. To use learned features from a large dataset to help a new task

B. To train a model from scratch with random weights

C. To increase the size of the dataset automatically

D. To reduce the number of layers in the model

Solution

1. Step 1: Understand feature extraction concept

   Feature extraction uses a pre-trained model to get useful features learned from a large dataset.

2. Step 2: Identify the benefit for new tasks

   This helps when you have little data or want faster training by reusing learned features.

3. Final Answer:

   To use learned features from a large dataset to help a new task -> Option A

4. Quick Check:

   Feature extraction = reuse learned features [OK]

Hint: Feature extraction reuses knowledge from big datasets [OK]

Common Mistakes:

• Thinking feature extraction trains from scratch
• Confusing feature extraction with data augmentation
• Believing it reduces model layers automatically

2. Which TensorFlow code snippet correctly freezes the base model layers for feature extraction?

easy

A. base_model.trainable = True

B. base_model.trainable = False

C. base_model.freeze()

D. base_model.layers.freeze = True

Solution

1. Step 1: Recall how to freeze layers in TensorFlow

   Setting trainable = False on the base model freezes its weights.

2. Step 2: Check each option's correctness

   base_model.trainable = False correctly sets base_model.trainable = False. Others are invalid syntax or do not freeze layers.

3. Final Answer:

   base_model.trainable = False -> Option B

4. Quick Check:

   Freeze layers = trainable False [OK]

Hint: Freeze layers by setting trainable to False [OK]

Common Mistakes:

• Using trainable = True to freeze layers
• Calling non-existent freeze() method
• Trying to set freeze attribute on layers directly

3. Given this code, what is the output shape of features?

base_model = tf.keras.applications.MobileNetV2(input_shape=(128,128,3), include_top=False)
base_model.trainable = False
inputs = tf.keras.Input(shape=(128,128,3))
features = base_model(inputs)
print(features.shape)

medium

A. (None, 4, 4, 1280)

B. (None, 7, 7, 512)

C. (None, 1, 1, 1000)

D. (None, 128, 128, 3)

Solution

1. Step 1: Understand MobileNetV2 output with include_top=False

   MobileNetV2 outputs feature maps of size (4,4,1280) for 128x128 input when top layers are excluded.

2. Step 2: Confirm batch dimension is None

   The batch size is None (unspecified), so output shape is (None, 4, 4, 1280).

3. Final Answer:

   (None, 4, 4, 1280) -> Option A

4. Quick Check:

   MobileNetV2 feature shape = (None,4,4,1280) [OK]

Hint: MobileNetV2 outputs 4x4x1280 features for 128x128 input [OK]

Common Mistakes:

• Confusing output with classification layer shape
• Assuming output shape equals input shape
• Ignoring batch dimension None

4. Identify the error in this feature extraction code snippet:

base_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False)
base_model.trainable = False
inputs = tf.keras.Input(shape=(224,224,3))
x = base_model(inputs)
x = tf.keras.layers.Dense(10)(x)
model = tf.keras.Model(inputs, x)

medium

A. Base model weights not loaded correctly

B. Input shape is incorrect for ResNet50

C. Dense layer applied to 4D tensor without flattening

D. trainable should be True to freeze layers

Solution

1. Step 1: Check tensor shapes before Dense layer

   Base model outputs 4D tensor (batch, height, width, channels). Dense expects 2D input.

2. Step 2: Identify missing flatten or global pooling

   Applying Dense directly to 4D tensor causes error; flatten or global pooling needed first.

3. Final Answer:

   Dense layer applied to 4D tensor without flattening -> Option C

4. Quick Check:

   Dense needs 2D input, flatten first [OK]

Hint: Flatten or pool before Dense layer [OK]

Common Mistakes:

• Applying Dense directly to 4D output
• Confusing input shape requirements
• Misunderstanding trainable flag usage

5. You want to use feature extraction with MobileNetV2 on 64x64 images but get an error when adding a Dense layer after the base model. What is the best way to fix this?

hard

A. Set base_model.trainable = True to allow training

B. Change input shape to 224x224 to match MobileNetV2 default

C. Remove the Dense layer and use base model output directly

D. Add a GlobalAveragePooling2D layer before the Dense layer

Solution

1. Step 1: Understand why Dense layer causes error

   MobileNetV2 outputs 4D feature maps; Dense layers need 2D input.

2. Step 2: Use GlobalAveragePooling2D to convert 4D to 2D

   Adding GlobalAveragePooling2D flattens spatial dimensions, making output suitable for Dense.

3. Step 3: Evaluate other options

   Changing input size is not required; training base model is optional; removing Dense loses classification ability.

4. Final Answer:

   Add a GlobalAveragePooling2D layer before the Dense layer -> Option D

5. Quick Check:

   Pool features before Dense layer [OK]

Hint: Use pooling to flatten features before Dense [OK]

Common Mistakes:

• Changing input size unnecessarily
• Trying to train frozen base model
• Skipping pooling and causing shape errors