Feature extraction approach in TensorFlow

Introduction

Feature extraction helps us get important information from data so the computer can learn better and faster.

When you want to use a pre-trained model to get useful data features without training from scratch.

When your dataset is small and training a full model is hard.

When you want to speed up training by reusing learned features.

When you want to improve model accuracy by using strong, tested features.

When you want to understand which parts of data are important for predictions.

Syntax

TensorFlow

base_model = tf.keras.applications.MobileNetV2(input_shape=(224,224,3), include_top=False, weights='imagenet')
base_model.trainable = False

inputs = tf.keras.Input(shape=(224,224,3))
x = base_model(inputs, training=False)
x = tf.keras.layers.GlobalAveragePooling2D()(x)
outputs = tf.keras.layers.Dense(1, activation='sigmoid')(x)
model = tf.keras.Model(inputs, outputs)

Set include_top=False to remove the final classification layer and get features.

Freeze the base model weights by setting trainable = False to avoid changing pre-trained features.

Examples

Using ResNet50 as the feature extractor without its top layer.

TensorFlow

base_model = tf.keras.applications.ResNet50(include_top=False, weights='imagenet')
base_model.trainable = False

Extract features and add new layers for a 10-class classification task.

TensorFlow

x = base_model(inputs, training=False)
x = tf.keras.layers.Flatten()(x)
outputs = tf.keras.layers.Dense(10, activation='softmax')(x)

Sample Model

This example shows how to use MobileNetV2 as a feature extractor. We freeze its weights, add new layers, train on dummy data, and make predictions.

TensorFlow

import tensorflow as tf

# Load pre-trained MobileNetV2 without top layer
base_model = tf.keras.applications.MobileNetV2(input_shape=(224,224,3), include_top=False, weights='imagenet')
base_model.trainable = False

# Build new model using feature extraction
inputs = tf.keras.Input(shape=(224,224,3))
x = base_model(inputs, training=False)
x = tf.keras.layers.GlobalAveragePooling2D()(x)
outputs = tf.keras.layers.Dense(1, activation='sigmoid')(x)
model = tf.keras.Model(inputs, outputs)

# Compile model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Create dummy data (10 images, 224x224 RGB) and labels
import numpy as np
data = np.random.random((10,224,224,3)).astype('float32')
labels = np.random.randint(0,2,size=(10,1))

# Train model for 2 epochs
history = model.fit(data, labels, epochs=2, verbose=2)

# Predict on new dummy data
predictions = model.predict(data[:2])
print('Predictions:', predictions.flatten())

Important Notes

Feature extraction saves time by reusing learned knowledge from big datasets.

Always preprocess input images the same way the pre-trained model expects.

Freezing the base model prevents losing the useful features it learned.

Summary

Feature extraction uses pre-trained models to get useful data features.

It helps when you have little data or want faster training.

Freeze the base model and add your own layers for your task.

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