Transfer learning for small datasets in TensorFlow - ML Experiment: Train & Evaluate

Experiment - Transfer learning for small datasets

Problem:You want to classify images into 3 categories using a small dataset of 300 images. The current model is a simple CNN trained from scratch.

Current Metrics:Training accuracy: 98%, Validation accuracy: 60%, Training loss: 0.05, Validation loss: 1.2

Issue:The model overfits badly: training accuracy is very high but validation accuracy is low, indicating poor generalization.

Your Task

Use transfer learning with a pre-trained model to improve validation accuracy to above 85% while reducing overfitting.

You must use TensorFlow and Keras.

You cannot increase the dataset size.

You should freeze the pre-trained layers initially.

You can add dropout or data augmentation.

Hint 1

Hint 2

Hint 3

Hint 4

Hint 5

Solution

TensorFlow

import tensorflow as tf
from tensorflow.keras import layers, models
from tensorflow.keras.applications import MobileNetV2
from tensorflow.keras.preprocessing.image import ImageDataGenerator

# Load pre-trained MobileNetV2 without top layers
base_model = MobileNetV2(input_shape=(128,128,3), include_top=False, weights='imagenet')
base_model.trainable = False

# Add classification head
model = models.Sequential([
    base_model,
    layers.GlobalAveragePooling2D(),
    layers.Dropout(0.3),
    layers.Dense(3, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

# Data augmentation
train_datagen = ImageDataGenerator(
    rescale=1./255,
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    horizontal_flip=True,
    validation_split=0.2
)

train_generator = train_datagen.flow_from_directory(
    'data/train',
    target_size=(128,128),
    batch_size=32,
    class_mode='sparse',
    subset='training'
)

validation_generator = train_datagen.flow_from_directory(
    'data/train',
    target_size=(128,128),
    batch_size=32,
    class_mode='sparse',
    subset='validation'
)

history = model.fit(
    train_generator,
    epochs=15,
    validation_data=validation_generator
)

# Optionally unfreeze some layers and fine-tune
base_model.trainable = True
fine_tune_at = 100
for layer in base_model.layers[:fine_tune_at]:
    layer.trainable = False

model.compile(optimizer=tf.keras.optimizers.Adam(1e-5),
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

fine_tune_history = model.fit(
    train_generator,
    epochs=10,
    validation_data=validation_generator
)

Replaced simple CNN with MobileNetV2 pre-trained on ImageNet.

Froze base model layers to prevent overfitting on small data.

Added dropout layer to reduce overfitting.

Used data augmentation to increase effective dataset size.

Fine-tuned top layers of base model with low learning rate.

Results Interpretation

Before: Training accuracy 98%, Validation accuracy 60%, high overfitting.

After: Training accuracy 90%, Validation accuracy 87%, much better generalization.

Transfer learning with a pre-trained model and freezing layers helps prevent overfitting on small datasets. Data augmentation and dropout further improve validation accuracy.

Bonus Experiment

Try using a different pre-trained model like ResNet50 and compare validation accuracy.

💡 Hint

ResNet50 has a different architecture and may perform better or worse depending on your data. Adjust dropout and learning rate accordingly.

Practice

1. What is the main reason to use transfer learning when working with small datasets in TensorFlow?

easy

A. To increase the size of the dataset automatically

B. To use a pretrained model's knowledge and avoid training from scratch

C. To reduce the number of layers in the model

D. To train all layers of a model from random weights

Solution

1. Step 1: Understand transfer learning purpose

   Transfer learning uses a pretrained model to leverage learned features from large datasets.

2. Step 2: Relate to small dataset challenges

   Small datasets lack enough data to train deep models well, so using pretrained knowledge helps.

3. Final Answer:

   To use a pretrained model's knowledge and avoid training from scratch -> Option B

4. Quick Check:

   Transfer learning = pretrained knowledge reuse [OK]

Hint: Transfer learning reuses pretrained features for small data [OK]

Common Mistakes:

• Thinking transfer learning increases dataset size
• Believing all layers must be retrained
• Assuming transfer learning reduces model layers

2. Which TensorFlow code snippet correctly freezes the base model layers for transfer learning?

easy

A. base_model.freeze_layers()

B. base_model.trainable = True

C. base_model.trainable = False

D. base_model.layers.freeze()

Solution

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

   Setting trainable = False on the base model freezes all its layers.

2. Step 2: Check code options

   Only base_model.trainable = False is valid TensorFlow syntax to freeze layers.

3. Final Answer:

   base_model.trainable = False -> Option C

4. Quick Check:

   Freeze layers = trainable False [OK]

Hint: Set base_model.trainable = False to freeze layers [OK]

Common Mistakes:

• Using trainable = True instead of False
• Calling non-existent freeze_layers() method
• Trying to freeze layers with base_model.layers.freeze()

3. Given this code snippet, what will be the output shape of the model's predictions?

import tensorflow as tf
base_model = tf.keras.applications.MobileNetV2(input_shape=(128,128,3), include_top=False, pooling='avg')
base_model.trainable = False
model = tf.keras.Sequential([
  base_model,
  tf.keras.layers.Dense(10, activation='softmax')
])
model.build((None, 128, 128, 3))
predictions = model(tf.random.uniform((5, 128, 128, 3)))
print(predictions.shape)

medium

A. (5, 1)

B. (5, 128, 128, 3)

C. (5, 1000)

D. (5, 10)

Solution

1. Step 1: Analyze model architecture

   MobileNetV2 outputs pooled features (shape: (None, 1280)) due to pooling='avg'. Then Dense(10) outputs 10 classes.

2. Step 2: Check input batch size and output shape

   Input batch size is 5, so output shape is (5, 10) from Dense layer.

3. Final Answer:

   (5, 10) -> Option D

4. Quick Check:

   Batch 5, 10 classes output shape = (5, 10) [OK]

Hint: Output shape matches batch size and last Dense units [OK]

Common Mistakes:

• Confusing input shape with output shape
• Expecting output shape to match input image shape
• Assuming output has 1000 classes from original MobileNet

4. You wrote this code but get an error when training:

base_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False)
base_model.trainable = False
model = tf.keras.Sequential([
  base_model,
  tf.keras.layers.Dense(5, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.fit(train_data, epochs=3)

What is the likely cause of the error?

medium

A. Missing input shape in base_model causing shape mismatch

B. trainable should be True to train the model

C. Loss function is incorrect for classification

D. Dense layer should have no activation

Solution

1. Step 1: Check base_model input shape requirement

   ResNet50 requires input_shape when include_top=False to build properly.

2. Step 2: Identify error cause

   Without input_shape, model layers don't connect correctly, causing training errors.

3. Final Answer:

   Missing input shape in base_model causing shape mismatch -> Option A

4. Quick Check:

   Input shape needed for base_model [OK]

Hint: Always specify input_shape when include_top=False [OK]

Common Mistakes:

• Not specifying input_shape for pretrained base model
• Thinking trainable must be True to avoid errors
• Changing loss function unnecessarily

5. You have a small dataset of 200 images for a 3-class classification task. Which transfer learning approach is best to get good accuracy quickly?

hard

A. Use a pretrained model, freeze base layers, add new Dense layers, train only new layers

B. Train a new model from scratch with random weights

C. Use a pretrained model and train all layers without freezing

D. Use a pretrained model without adding new layers and train only base layers

Solution

1. Step 1: Consider dataset size and training time

   Small dataset (200 images) benefits from freezing pretrained base to avoid overfitting and long training.

2. Step 2: Choose transfer learning strategy

   Freezing base layers and training new Dense layers adapts model to new task efficiently.

3. Final Answer:

   Use a pretrained model, freeze base layers, add new Dense layers, train only new layers -> Option A

4. Quick Check:

   Freeze base + train new layers = best for small data [OK]

Hint: Freeze base layers, train new layers for small datasets [OK]

Common Mistakes:

• Training all layers on small data causing overfitting
• Training from scratch wasting time and data
• Not adding new layers for the specific task