Inception modules in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the InceptionV3 model from Keras applications.

Computer Vision

from tensorflow.keras.applications import [1]

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

AResNet50

BMobileNet

CInceptionV3

DVGG16

Attempts:

3 left

💡 Hint

Common Mistakes

Importing a different model like ResNet50 or VGG16 instead of InceptionV3.

The InceptionV3 model is imported from tensorflow.keras.applications using 'InceptionV3'.

2fill in blank

medium

Complete the code to create an InceptionV3 model without the top classification layer.

Computer Vision

model = InceptionV3(weights='imagenet', include_top=[1])

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

ATrue

BNone

C'imagenet'

DFalse

Attempts:

3 left

💡 Hint

Common Mistakes

Setting include_top=True which keeps the original classification layers.

Setting include_top=False removes the final classification layers, allowing customization.

3fill in blank

hard

Fix the error in the code to add a global average pooling layer after the Inception base.

Computer Vision

from tensorflow.keras.layers import GlobalAveragePooling2D
x = model.output
x = [1](x)

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

AGlobalAveragePooling2D

BDense

CGlobalMaxPooling2D

DFlatten

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dense or Flatten which are not pooling layers.

Using GlobalMaxPooling2D which uses max instead of average.

GlobalAveragePooling2D reduces each feature map to a single value by averaging, suitable after convolutional layers.

4fill in blank

hard

Fill both blanks to add a dense output layer with 10 classes and softmax activation.

Computer Vision

from tensorflow.keras.layers import Dense
outputs = Dense([1], activation=[2])(x)

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

A10

B'softmax'

C'relu'

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using relu activation in the output layer.

Setting units to 1 instead of 10.

The output layer has 10 units for 10 classes and uses softmax activation for probabilities.

5fill in blank

hard

Fill all three blanks to compile the model with Adam optimizer, categorical crossentropy loss, and accuracy metric.

Computer Vision

model.compile(optimizer=[1], loss=[2], metrics=[[3]])

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

A'adam'

B'categorical_crossentropy'

C'accuracy'

D'mse'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'mse' loss which is for regression.

Using wrong metric like 'mse' instead of 'accuracy'.

Adam optimizer is popular; categorical crossentropy is used for multi-class classification; accuracy measures correct predictions.

Practice

1. What is the main purpose of using 1x1 convolutions in an Inception module?

easy

A. To increase the spatial size of the feature maps

B. To add non-linearity without changing dimensions

C. To replace max pooling layers

D. To reduce the number of channels and keep the model efficient

Solution

1. Step 1: Understand the role of 1x1 convolutions

   1x1 convolutions act as channel-wise feature selectors and reduce the number of channels, lowering computation.

2. Step 2: Connect to Inception module efficiency

   By reducing channels before expensive convolutions, the model stays efficient without losing important information.

3. Final Answer:

   To reduce the number of channels and keep the model efficient -> Option D

4. Quick Check:

   1x1 convolutions reduce channels = B [OK]

Hint: 1x1 convs reduce channels to save computation [OK]

Common Mistakes:

• Thinking 1x1 convs increase spatial size
• Confusing 1x1 convs with pooling layers
• Assuming 1x1 convs only add non-linearity

2. Which of the following is the correct way to combine outputs from different branches in an Inception module?

easy

A. Concatenate the outputs along the channel dimension

B. Use max pooling on all outputs

C. Multiply the outputs element-wise

D. Add the outputs element-wise

Solution

1. Step 1: Identify how Inception combines branch outputs

   Inception modules concatenate outputs from different filter branches along the channel axis to keep all features.

2. Step 2: Understand why concatenation is used

   Concatenation preserves all features from each branch, unlike addition or multiplication which mix them.

3. Final Answer:

   Concatenate the outputs along the channel dimension -> Option A

4. Quick Check:

   Outputs concatenated by channels = D [OK]

Hint: Inception outputs join by channel concat, not add [OK]

Common Mistakes:

• Confusing concatenation with element-wise addition
• Thinking outputs are multiplied
• Assuming pooling merges outputs

3. Given this simplified Inception module code snippet, what is the shape of the output tensor?

import torch
import torch.nn as nn

class SimpleInception(nn.Module):
    def __init__(self):
        super().__init__()
        self.branch1 = nn.Conv2d(192, 64, kernel_size=1)
        self.branch2 = nn.Conv2d(192, 128, kernel_size=3, padding=1)
        self.branch3 = nn.Conv2d(192, 32, kernel_size=5, padding=2)
    def forward(self, x):
        b1 = self.branch1(x)
        b2 = self.branch2(x)
        b3 = self.branch3(x)
        return torch.cat([b1, b2, b3], dim=1)

input_tensor = torch.randn(1, 192, 28, 28)
model = SimpleInception()
output = model(input_tensor)
print(output.shape)

medium

A. (1, 224, 32, 32)

B. (1, 64, 28, 28)

C. (1, 224, 28, 28)

D. (1, 224, 28, 28, 3)

Solution

1. Step 1: Calculate output channels per branch

   Branch1 outputs 64 channels, branch2 outputs 128, branch3 outputs 32. Total channels = 64+128+32 = 224.

2. Step 2: Check spatial dimensions and concatenation

   All convolutions use padding to keep spatial size 28x28. Concatenation along channel dimension keeps height and width same.

3. Final Answer:

   (1, 224, 28, 28) -> Option C

4. Quick Check:

   Channels sum to 224, spatial unchanged = A [OK]

Hint: Sum channels from branches, keep spatial size same [OK]

Common Mistakes:

• Adding spatial dimensions instead of channels
• Ignoring padding effects on size
• Misunderstanding concat dimension

4. Identify the error in this Inception module implementation:

class FaultyInception(nn.Module):
    def __init__(self):
        super().__init__()
        self.branch1 = nn.Conv2d(128, 32, kernel_size=1)
        self.branch2 = nn.Conv2d(128, 64, kernel_size=3, padding=1)
    def forward(self, x):
        b1 = self.branch1(x)
        b2 = self.branch2(x)
        return torch.cat([b1, b2], dim=2)

medium

A. Missing padding in branch2 convolution

B. Concatenation dimension should be 1, not 2

C. Input channels to branch1 are incorrect

D. Using nn.Conv2d instead of nn.Conv1d

Solution

1. Step 1: Check concatenation dimension

   In PyTorch, channel dimension is 1. Concatenating along dim=2 (height) is incorrect for Inception outputs.

2. Step 2: Confirm other parts

   Branch2 padding keeps spatial size consistent; input channels match; Conv2d is correct for images.

3. Final Answer:

   Concatenation dimension should be 1, not 2 -> Option B

4. Quick Check:

   Concat along channels = dim 1 [OK]

Hint: Concat outputs along channel dim (1), not height (2) [OK]

Common Mistakes:

• Concatenating along wrong dimension
• Confusing padding with error
• Misreading input channel sizes

5. You want to design an Inception module that balances feature diversity and computational cost. Which combination best achieves this?

hard

A. Use 1x1 convolutions before 3x3 and 5x5 convolutions, then concatenate outputs

B. Use only 5x5 convolutions without 1x1 convolutions to capture large features

C. Use max pooling only and skip convolutions to reduce cost

D. Stack multiple 3x3 convolutions without any 1x1 convolutions

Solution

1. Step 1: Understand feature diversity and cost tradeoff

   Large filters capture diverse features but are costly. 1x1 convolutions reduce channels before large filters to save cost.

2. Step 2: Evaluate options

   Use 1x1 convolutions before 3x3 and 5x5 convolutions, then concatenate outputs uses 1x1 convs to reduce channels before 3x3 and 5x5, balancing diversity and efficiency. Others either ignore cost or diversity.

3. Final Answer:

   Use 1x1 convolutions before 3x3 and 5x5 convolutions, then concatenate outputs -> Option A

4. Quick Check:

   1x1 convs reduce cost + multi-filter concat = C [OK]

Hint: Use 1x1 convs before big filters for efficiency [OK]

Common Mistakes:

• Ignoring 1x1 convs and increasing cost
• Using only pooling loses feature richness
• Stacking without channel reduction wastes resources