Pre-trained models (VGG, ResNet, MobileNet) in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the VGG16 pre-trained model without the top classification layer.

TensorFlow

from tensorflow.keras.applications import VGG16
model = VGG16(include_top=[1], weights='imagenet')

Drag options to blanks, or click blank then click option'

ATrue

B'imagenet'

CFalse

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using include_top=True when you want to customize the output.

Passing weights=None instead of 'imagenet'.

Setting include_top=False loads the model without the final classification layers, useful for feature extraction.

2fill in blank

medium

Complete the code to preprocess input images for ResNet50 model.

TensorFlow

from tensorflow.keras.applications.resnet50 import preprocess_input
preprocessed_img = preprocess_input([1])

Drag options to blanks, or click blank then click option'

Araw_image

Bmodel

Cinput_shape

Dpredictions

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the model object instead of image data.

Passing predictions instead of raw images.

The preprocess_input function expects raw image data to prepare it for the model.

3fill in blank

hard

Fix the error in the code to correctly load MobileNet with input shape 128x128x3.

TensorFlow

from tensorflow.keras.applications import MobileNet
model = MobileNet(input_shape=[1], weights='imagenet', include_top=False)

Drag options to blanks, or click blank then click option'

A(128, 128, 3)

B[128, 128, 3]

C128, 128, 3

D'128x128x3'

Attempts:

3 left

💡 Hint

Common Mistakes

Using list brackets instead of tuple parentheses.

Passing a string instead of a tuple.

The input_shape argument requires a tuple specifying the dimensions.

4fill in blank

hard

Fill both blanks to create a feature extractor from ResNet50 and freeze its layers.

TensorFlow

from tensorflow.keras.applications import ResNet50
model = ResNet50(include_top=[1], weights='imagenet')
model.[2] = False

Drag options to blanks, or click blank then click option'

AFalse

BTrue

Ctrainable

Dcompile

Attempts:

3 left

💡 Hint

Common Mistakes

Using include_top=True when freezing layers.

Trying to freeze layers by calling compile instead of setting trainable.

Setting include_top=False removes the classification layers. Setting model.trainable = False freezes the model weights.

5fill in blank

hard

Fill all three blanks to build a simple classifier on top of MobileNet features.

TensorFlow

from tensorflow.keras.applications import MobileNet
from tensorflow.keras import layers, models
base_model = MobileNet(include_top=[1], weights='imagenet', input_shape=(224,224,3))
base_model.trainable = [2]
model = models.Sequential([
    base_model,
    layers.GlobalAveragePooling2D(),
    layers.Dense([3], activation='softmax')
])

Drag options to blanks, or click blank then click option'

AFalse

BTrue

C10

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Setting include_top=True when adding custom layers.

Not freezing the base model causing slow training.

Using None instead of number of classes in Dense layer.

We exclude the top layer (include_top=False) to add our own classifier. We freeze the base model (trainable=False) to keep pre-trained weights fixed. The final Dense layer has 10 units for 10 classes.

Practice

1. Which of the following is a key benefit of using pre-trained models like VGG, ResNet, or MobileNet in TensorFlow?

easy

A. They require training from scratch for every new task.

B. They cannot be fine-tuned for new tasks.

C. They only work with text data, not images.

D. They save time by using models already trained on large datasets.

Solution

1. Step 1: Understand what pre-trained models are

   Pre-trained models are AI models trained on large datasets like ImageNet before you use them.

2. Step 2: Identify the main advantage

   Using these models saves time because you don't need to train from zero; you can use their learned features directly.

3. Final Answer:

   They save time by using models already trained on large datasets. -> Option D

4. Quick Check:

   Pre-trained models save time = B [OK]

Hint: Pre-trained means already trained, so saves time [OK]

Common Mistakes:

• Thinking pre-trained models need full retraining
• Believing they only work on text data
• Assuming they cannot be fine-tuned

2. Which of the following is the correct way to load the MobileNetV2 pre-trained model in TensorFlow with weights trained on ImageNet?

easy

A. tf.keras.MobileNetV2(weights='imagenet')

B. tf.keras.applications.MobileNetV2(weights='imagenet')

C. tf.keras.applications.MobileNet(weights='imagenet')

D. tf.keras.applications.MobileNetV2(weights='random')

Solution

1. Step 1: Recall the correct TensorFlow module for pre-trained models

   Pre-trained models are loaded from tf.keras.applications, not directly from tf.keras.

2. Step 2: Check the correct model name and weights argument

   The correct model name is MobileNetV2 and weights='imagenet' loads pre-trained weights.

3. Final Answer:

   tf.keras.applications.MobileNetV2(weights='imagenet') -> Option B

4. Quick Check:

   Use tf.keras.applications + correct model name + weights='imagenet' = A [OK]

Hint: Use tf.keras.applications.ModelName(weights='imagenet') [OK]

Common Mistakes:

• Using tf.keras.MobileNetV2 instead of tf.keras.applications.MobileNetV2
• Using wrong model name like MobileNet instead of MobileNetV2
• Setting weights='random' instead of 'imagenet'

3. What will be the output shape of the following code snippet using the ResNet50 model in TensorFlow?

import tensorflow as tf
model = tf.keras.applications.ResNet50(weights='imagenet')
input_shape = (1, 224, 224, 3)
sample_input = tf.random.uniform(input_shape)
output = model(sample_input)
print(output.shape)

medium

A. (1, 7, 7, 2048)

B. (224, 224, 3)

C. (1, 1000)

D. (1, 100)

Solution

1. Step 1: Understand ResNet50 output for ImageNet weights

   ResNet50 with weights='imagenet' outputs predictions for 1000 classes, so output shape is (batch_size, 1000).

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

   Input batch size is 1, so output shape is (1, 1000).

3. Final Answer:

   (1, 1000) -> Option C

4. Quick Check:

   ResNet50 output shape = (batch_size, 1000) = A [OK]

Hint: Output shape matches number of ImageNet classes (1000) [OK]

Common Mistakes:

• Confusing output with input shape
• Expecting feature map shape instead of final predictions
• Assuming output has spatial dimensions

4. You tried to load the VGG16 model with this code:

model = tf.keras.applications.VGG16(weights='imagenet', include_top=False, input_shape=(28,28,3))

But got an error. What is the likely cause?

medium

A. Input shape must be at least 32x32 with 3 channels when include_top=False.

B. Weights='imagenet' is not supported for VGG16.

C. include_top=False cannot be used with input_shape argument.

D. VGG16 requires grayscale images, so 3 channels is wrong.

Solution

1. Step 1: Check VGG16 input shape requirements

   When include_top=False, VGG16 requires input images at least 32x32 pixels with 3 color channels.

2. Step 2: Verify input shape given

   Input shape (28,28,3) is smaller than 32x32x3 minimum when include_top=False, causing the error.

3. Step 3: Identify common mistake

   Often error happens if input_shape is smaller than 32x32 or channels not 3. The question implies error due to input shape constraints.

4. Final Answer:

   Input shape must be at least 32x32 with 3 channels when include_top=False. -> Option A

5. Quick Check:

   VGG16 input shape min size = 32x32x3 [OK]

Hint: VGG16 needs input ≥32x32x3 if include_top=False [OK]

Common Mistakes:

• Thinking weights='imagenet' is unsupported
• Believing include_top=False forbids input_shape
• Assuming VGG16 uses grayscale images

5. You want to build a fast image classifier for mobile devices using TensorFlow. Which pre-trained model should you choose to balance speed and accuracy?

hard

A. MobileNet, because it is designed for lightweight and fast inference.

B. ResNet50, because it uses residual connections for better training.

C. InceptionV3, because it has the most complex architecture.

D. VGG19, because it has the deepest layers and highest accuracy.

Solution

1. Step 1: Understand model design goals

   VGG19 is large and slow, ResNet50 is accurate but heavier, MobileNet is optimized for mobile with smaller size and speed.

2. Step 2: Match model to mobile device needs

   Mobile devices need fast, lightweight models, so MobileNet fits best for balancing speed and accuracy.

3. Final Answer:

   MobileNet, because it is designed for lightweight and fast inference. -> Option A

4. Quick Check:

   MobileNet = lightweight + fast for mobile [OK]

Hint: MobileNet is made for mobile speed and size [OK]

Common Mistakes:

• Choosing VGG19 for mobile despite size
• Assuming ResNet50 is fastest
• Picking InceptionV3 without speed consideration