Feature extraction approach in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Feature extraction approach

Which metric matters for Feature Extraction and WHY

Feature extraction helps turn raw data into useful information for a model. The key metrics to check are model accuracy, precision, and recall after using extracted features. These metrics show if the features help the model make better predictions.

Accuracy tells how often the model is right overall. Precision shows how many predicted positives are truly positive. Recall shows how many actual positives the model finds. Good features improve these numbers.

Confusion Matrix Example

      Actual \ Predicted | Positive | Negative
      -------------------|----------|---------
      Positive           |    TP=80 |   FN=20
      Negative           |    FP=10 |   TN=90
    

From this matrix:

• Precision = 80 / (80 + 10) = 0.89
• Recall = 80 / (80 + 20) = 0.80
• Accuracy = (80 + 90) / 200 = 0.85

This shows how well the features help the model separate classes.

Precision vs Recall Tradeoff with Feature Extraction

Feature extraction can affect precision and recall differently. For example:

• If features miss important details, recall drops (model misses positives).
• If features add noise, precision drops (model predicts too many false positives).

Example: In medical diagnosis, high recall is critical to catch all sick patients, even if precision is lower. In spam detection, high precision is important to avoid marking good emails as spam.

Good vs Bad Metric Values for Feature Extraction

Good: Accuracy > 80%, Precision and Recall both above 75%. This means features help the model find and correctly identify important patterns.

Bad: Accuracy around 50-60%, Precision or Recall very low (below 50%). This means features are not informative or add noise, hurting model performance.

Common Pitfalls in Feature Extraction Metrics

• Accuracy paradox: High accuracy but poor recall or precision can mislead about feature quality.
• Data leakage: Features accidentally include future or target info, inflating metrics falsely.
• Overfitting: Features too specific to training data cause high training metrics but poor test results.
• Ignoring class imbalance: Metrics like accuracy can be misleading if classes are uneven.

Self Check

Your model uses extracted features and shows 98% accuracy but only 12% recall on fraud cases. Is it good?

Answer: No. The low recall means the model misses most fraud cases, which is critical to detect. Despite high accuracy, the features do not help find fraud well. You should improve feature extraction to increase recall.

Key Result

Feature extraction quality is best judged by balanced precision and recall improvements, not just accuracy.

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