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.