U-Net architecture in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the correct layer for convolution in U-Net.

Computer Vision

from tensorflow.keras.layers import [1]

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

ADense

BFlatten

CLSTM

DConv2D

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dense layer instead of Conv2D

Using LSTM which is for sequences

The U-Net architecture uses 2D convolutional layers to process image data. Conv2D is the correct layer to use.

2fill in blank

medium

Complete the code to define the input shape for a U-Net model processing 128x128 RGB images.

Computer Vision

inputs = Input(shape=[1])

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

A(128, 128, 3)

B(256, 256, 3)

C(3, 128, 128)

D(128, 128)

Attempts:

3 left

💡 Hint

Common Mistakes

Omitting the channel dimension

Using wrong order of dimensions

The input shape for RGB images includes height, width, and 3 color channels. So (128, 128, 3) is correct.

3fill in blank

hard

Fix the error in the code to correctly add a max pooling layer in U-Net.

Computer Vision

pool1 = [1](2, 2)(conv1)

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

AMaxPooling1D

BMaxPooling2D

CAveragePooling2D

DGlobalMaxPooling2D

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1D pooling instead of 2D

Using average pooling instead of max pooling

MaxPooling2D is used to reduce spatial dimensions in 2D images. MaxPooling1D is for sequences, so it's incorrect here.

4fill in blank

hard

Fill both blanks to correctly concatenate skip connection features in U-Net.

Computer Vision

merge1 = Concatenate(axis=[1])([[2], up1])

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

A3

B2

Cconv1

Dpool1

Attempts:

3 left

💡 Hint

Common Mistakes

Concatenating along wrong axis

Using pooling layer instead of convolution features

Concatenation in U-Net happens along the channel axis, which is axis 3 in TensorFlow's channel-last format. The skip connection uses conv1 features.

5fill in blank

hard

Fill all three blanks to complete the output layer of U-Net for binary segmentation.

Computer Vision

outputs = Conv2D([1], (1, 1), activation=[2])([3])

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

A1

B'sigmoid'

Cconv10

D'softmax'

Attempts:

3 left

💡 Hint

Common Mistakes

Using softmax activation for binary output

Using multiple filters instead of 1

For binary segmentation, the output layer has 1 filter with sigmoid activation applied to the last convolution layer conv10.

Practice

1. What is the main purpose of the U-Net architecture in computer vision?

easy

A. To compress images for storage

B. To classify images into categories

C. To find exact shapes and boundaries in images

D. To generate new images from noise

Solution

1. Step 1: Understand U-Net's design goal

   U-Net is designed to segment images, meaning it finds exact shapes and boundaries.

2. Step 2: Compare with other tasks

   Classification assigns labels, generation creates images, compression reduces size; these are not U-Net's main tasks.

3. Final Answer:

   To find exact shapes and boundaries in images -> Option C

4. Quick Check:

   U-Net = segmentation [OK]

Hint: U-Net = image segmentation for shapes [OK]

Common Mistakes:

• Confusing segmentation with classification
• Thinking U-Net generates images
• Assuming U-Net compresses images

2. Which of the following correctly describes the structure of U-Net?

easy

A. Two paths: one shrinks and one expands the image size

B. A single path that shrinks the image size

C. A path that only expands the image size

D. Multiple independent paths without connection

Solution

1. Step 1: Recall U-Net architecture parts

   U-Net has an encoder path that shrinks and a decoder path that expands the image size.

2. Step 2: Eliminate incorrect options

   Single shrinking path or only expanding path do not match U-Net. Independent paths without connection are incorrect.

3. Final Answer:

   Two paths: one shrinks and one expands the image size -> Option A

4. Quick Check:

   U-Net = encoder + decoder [OK]

Hint: U-Net has encoder and decoder paths [OK]

Common Mistakes:

• Thinking U-Net only shrinks images
• Believing U-Net only expands images
• Ignoring the connection between paths

3. Consider this simplified U-Net code snippet in Python using PyTorch:

import torch
import torch.nn as nn

class SimpleUNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.down = nn.Conv2d(1, 16, 3, padding=1)
        self.up = nn.ConvTranspose2d(16, 1, 2, stride=2)

    def forward(self, x):
        x1 = self.down(x)  # shrink
        x2 = self.up(x1)   # expand
        return x2

model = SimpleUNet()
input_tensor = torch.randn(1, 1, 64, 64)
output = model(input_tensor)
print(output.shape)

What will be the printed output shape?

medium

A. torch.Size([1, 1, 64, 64])

B. torch.Size([1, 1, 128, 128])

C. torch.Size([1, 16, 64, 64])

D. torch.Size([1, 16, 32, 32])

Solution

1. Step 1: Analyze down convolution output size

   Input is 64x64, Conv2d with kernel=3, padding=1 keeps size 64x64, output channels=16.

2. Step 2: Analyze up convolution output size

   ConvTranspose2d with kernel=2, stride=2 doubles spatial size to 128x128, output channels=1.

3. Step 3: Check actual output shape

   Output shape is (batch=1, channels=1, height=128, width=128).

4. Final Answer:

   torch.Size([1, 1, 128, 128]) -> Option B

5. Quick Check:

   Upsample doubles size = 128x128 [OK]

Hint: ConvTranspose2d with stride 2 doubles size [OK]

Common Mistakes:

• Assuming Conv2d changes size without padding
• Ignoring stride effect in ConvTranspose2d
• Mixing channel numbers in output

4. In a U-Net implementation, a student forgot to add skip connections between encoder and decoder layers. What is the most likely effect?

medium

A. The model will not train at all and cause an error

B. The model will have better accuracy due to fewer connections

C. The model will run faster and produce the same results

D. The model will lose fine details and perform worse on segmentation

Solution

1. Step 1: Understand skip connections role

   Skip connections pass fine details from encoder to decoder to improve segmentation accuracy.

2. Step 2: Effect of missing skip connections

   Without them, decoder lacks detail info, causing worse segmentation results.

3. Final Answer:

   The model will lose fine details and perform worse on segmentation -> Option D

4. Quick Check:

   Skip connections = better detail [OK]

Hint: No skip connections = loss of detail [OK]

Common Mistakes:

• Thinking fewer connections always improve accuracy
• Assuming model will error without skip connections
• Believing speed improves without accuracy loss

5. You want to improve a U-Net model's segmentation on small objects in medical images. Which change is most effective?

hard

A. Increase the depth of the encoder to capture more features

B. Remove skip connections to simplify the model

C. Use larger convolution kernels to cover bigger areas

D. Add more pooling layers to reduce spatial size aggressively

Solution

1. Step 1: Identify challenge with small objects

   Small objects need detailed features and context captured by deeper layers.

2. Step 2: Evaluate options

   Increasing encoder depth helps learn more features. Removing skip connections loses detail. Larger kernels may blur small details. More pooling reduces spatial resolution, losing small object info.

3. Final Answer:

   Increase the depth of the encoder to capture more features -> Option A

4. Quick Check:

   Deeper encoder = better small object features [OK]

Hint: Deeper encoder = better small object detection [OK]

Common Mistakes:

• Removing skip connections harms detail
• Larger kernels blur small features
• More pooling loses small object info