Inception modules in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of an Inception module in a convolutional neural network?

Imagine you want your model to look at an image in many ways at once, like using different sized glasses to see details and the big picture. What is the main purpose of an Inception module?

A To replace convolutional layers with fully connected layers for faster training.

B To reduce the number of layers in the network by merging all convolutions into one.

C To combine multiple convolution filters of different sizes to capture features at various scales simultaneously.

D To increase the image size before feeding it into the network.

💡 Hint

Think about how the module uses different filter sizes in parallel.

The Inception module uses multiple convolution filters of different sizes (like 1x1, 3x3, 5x5) in parallel to capture features at different scales. This helps the network learn both small details and larger patterns at the same time.

❓ Predict Output

intermediate

What is the output shape of this Inception module snippet?

Given an input tensor of shape (batch_size, 28, 28, 192), what will be the output shape after this Inception module block?

Computer Vision

import tensorflow as tf
from tensorflow.keras import layers

input_tensor = tf.keras.Input(shape=(28, 28, 192))

branch1 = layers.Conv2D(64, (1,1), padding='same', activation='relu')(input_tensor)
branch2 = layers.Conv2D(96, (1,1), padding='same', activation='relu')(input_tensor)
branch2 = layers.Conv2D(128, (3,3), padding='same', activation='relu')(branch2)
branch3 = layers.Conv2D(16, (1,1), padding='same', activation='relu')(input_tensor)
branch3 = layers.Conv2D(32, (5,5), padding='same', activation='relu')(branch3)
branch4 = layers.MaxPooling2D((3,3), strides=(1,1), padding='same')(input_tensor)
branch4 = layers.Conv2D(32, (1,1), padding='same', activation='relu')(branch4)

output = layers.concatenate([branch1, branch2, branch3, branch4], axis=-1)
model = tf.keras.Model(inputs=input_tensor, outputs=output)
print(model.output_shape)

A (None, 28, 28, 256)

B (None, 28, 28, 224)

C (None, 28, 28, 192)

D (None, 28, 28, 320)

💡 Hint

Add the number of filters from all branches for the last dimension.

The output channels are the sum of filters from all branches: 64 + 128 + 32 + 32 = 256. But note branch2 has 128 filters, branch1 64, branch3 32, branch4 32, total 256. Recalculate carefully.

❓ Model Choice

advanced

Which model architecture first introduced the Inception module?

Which famous convolutional neural network architecture first used the Inception module to improve performance and efficiency?

A AlexNet

B GoogLeNet (Inception v1)

C VGGNet

D ResNet

💡 Hint

It is also called Inception v1 and won the ImageNet challenge in 2014.

GoogLeNet, also known as Inception v1, introduced the Inception module in 2014. It used parallel convolutions of different sizes to improve accuracy and reduce parameters.

🧠 Conceptual

advanced

What technique in the Inception module uses 1x1 convolutions for dimensionality reduction before expensive convolutions?

In Inception modules, 1x1 convolutions are used before larger convolutions to reduce the number of channels. What is this technique called?

A Batch normalization

B Pooling

C Dropout

D Dimensionality reduction

💡 Hint

It helps reduce computation by lowering the number of input channels.

Dimensionality reduction uses 1x1 convolutions to reduce the number of channels before applying larger convolutions, saving computation and parameters.

🔧 Debug

expert

Why does this Inception module code raise a shape mismatch error?

Consider this code snippet for an Inception module. It raises a shape mismatch error during concatenation. What is the cause?

Computer Vision

import tensorflow as tf
from tensorflow.keras import layers

input_tensor = tf.keras.Input(shape=(28, 28, 192))

branch1 = layers.Conv2D(64, (3,3), padding='valid', activation='relu')(input_tensor)
branch2 = layers.Conv2D(96, (1,1), padding='same', activation='relu')(input_tensor)
branch2 = layers.Conv2D(128, (3,3), padding='same', activation='relu')(branch2)
branch3 = layers.Conv2D(16, (1,1), padding='same', activation='relu')(input_tensor)
branch3 = layers.Conv2D(32, (5,5), padding='same', activation='relu')(branch3)
branch4 = layers.MaxPooling2D((3,3), strides=(1,1), padding='same')(input_tensor)
branch4 = layers.Conv2D(32, (1,1), padding='same', activation='relu')(branch4)

output = layers.concatenate([branch1, branch2, branch3, branch4], axis=-1)
model = tf.keras.Model(inputs=input_tensor, outputs=output)
print(model.output_shape)

A branch1 uses 'valid' padding causing smaller spatial dimensions than other branches.

B branch4 uses max pooling with stride 1 causing shape mismatch.

C The input tensor shape is incompatible with 5x5 convolutions.

D Concatenation axis is incorrect; it should be axis=1.

💡 Hint

Check how padding affects output size in convolutions.

Using 'valid' padding in branch1 reduces the height and width by 0 or more pixels, while other branches use 'same' padding keeping sizes equal. This causes shape mismatch during concatenation.