Image segmentation basics in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load an image and resize it for segmentation.

TensorFlow

import tensorflow as tf
image = tf.io.read_file('image.jpg')
image = tf.image.decode_jpeg(image, channels=3)
image = tf.image.resize(image, [1])
print(image.shape)

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

A(64, 64)

B(128, 128)

C(512, 512)

D(256, 256)

Attempts:

3 left

💡 Hint

Common Mistakes

Using the wrong tuple format like [256, 256] instead of (256, 256).

Not resizing the image before feeding it to the model.

We resize the image to (256, 256) pixels, a common size for segmentation models.

2fill in blank

medium

Complete the code to normalize the image pixels between 0 and 1.

TensorFlow

image = tf.cast(image, tf.float32)
image = image [1] 255.0

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

A/

B+

C*

D-

Attempts:

3 left

💡 Hint

Common Mistakes

Multiplying by 255 instead of dividing.

Subtracting 255 which leads to negative values.

Dividing by 255.0 scales pixel values from 0-255 to 0-1.

3fill in blank

hard

Fix the error in the model output layer for binary segmentation.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(32, 3, activation='relu', padding='same'),
    tf.keras.layers.Conv2D(1, 1, activation=[1])
])

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

A'softmax'

B'sigmoid'

C'tanh'

D'relu'

Attempts:

3 left

💡 Hint

Common Mistakes

Using softmax which is for multi-class problems.

Using relu which does not limit output range.

For binary segmentation, the output layer uses sigmoid activation to predict probabilities between 0 and 1.

4fill in blank

hard

Fill both blanks to compile the model with appropriate loss and metric for segmentation.

TensorFlow

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

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

A'binary_crossentropy'

B'accuracy'

C'categorical_crossentropy'

D'mean_squared_error'

Attempts:

3 left

💡 Hint

Common Mistakes

Using categorical_crossentropy for binary segmentation.

Using mean_squared_error which is for regression.

Binary crossentropy is the right loss for binary segmentation; accuracy is a common metric to track.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps image filenames to their resized tensors if width {{BLANK_1}} 256 and height {{BLANK_2}} 256, using tf.image.resize with size {{BLANK_3}}.

TensorFlow

images = {filename: tf.image.resize(tf.io.decode_jpeg(tf.io.read_file(filename)), [3]) for filename in file_list if tf.shape(tf.io.decode_jpeg(tf.io.read_file(filename)))[1] [1] 256 and tf.shape(tf.io.decode_jpeg(tf.io.read_file(filename)))[0] [2] 256}

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

A==

B!=

C(256, 256)

D(128, 128)

Attempts:

3 left

💡 Hint

Common Mistakes

Using '!=' instead of '==' in conditions.

Resizing to a different size than the condition.

We check if width and height equal 256, then resize to (256, 256).

Practice

1. What is the main goal of image segmentation in TensorFlow?

easy

A. To compress images without losing quality

B. To label each pixel in an image with a class

C. To generate random noise images

D. To classify the entire image into one category

Solution

1. Step 1: Understand image segmentation purpose

   Image segmentation assigns a class label to every pixel, dividing the image into meaningful parts.

2. Step 2: Compare with other tasks

   Unlike classification, which labels the whole image, segmentation works at pixel level.

3. Final Answer:

   To label each pixel in an image with a class -> Option B

4. Quick Check:

   Image segmentation = pixel-wise labeling [OK]

Hint: Segmentation means labeling pixels, not whole images [OK]

Common Mistakes:

• Confusing segmentation with image classification
• Thinking segmentation compresses images
• Believing segmentation creates random images

2. Which TensorFlow layer is commonly used to extract features for image segmentation?

easy

A. Convolutional layer

B. Dense layer

C. Dropout layer

D. Flatten layer

Solution

1. Step 1: Identify feature extraction layers

   Convolutional layers scan images to find patterns and features useful for segmentation.

2. Step 2: Understand other layers' roles

   Dense layers are for classification, dropout prevents overfitting, flatten reshapes data but doesn't extract features.

3. Final Answer:

   Convolutional layer -> Option A

4. Quick Check:

   Feature extraction = convolutional layers [OK]

Hint: Convolutional layers find image features [OK]

Common Mistakes:

• Choosing dense layers for feature extraction
• Confusing flatten with convolution
• Ignoring convolution's role in images

3. What will be the shape of the output tensor after applying a softmax activation on a segmentation model predicting 3 classes for a 128x128 image?

medium

A. (128, 128, 3)

B. (3, 128, 128)

C. (128, 3, 128)

D. (128, 128)

Solution

1. Step 1: Understand output shape for segmentation

   Each pixel has a probability for each class, so output shape is height x width x classes.

2. Step 2: Apply to given image and classes

   Image size is 128x128, classes are 3, so output shape is (128, 128, 3).

3. Final Answer:

   (128, 128, 3) -> Option A

4. Quick Check:

   Output shape = (height, width, classes) [OK]

Hint: Output shape = image size + number of classes [OK]

Common Mistakes:

• Mixing class dimension position
• Forgetting classes dimension
• Using 2D shape instead of 3D

4. Given this TensorFlow code snippet for segmentation, what is the error?

model = tf.keras.Sequential([
  tf.keras.layers.Conv2D(16, 3, activation='relu', input_shape=(64, 64, 3)),
  tf.keras.layers.Dense(3, activation='softmax')
])

medium

A. Conv2D kernel size must be 1

B. Input shape is incorrect for images

C. Activation 'relu' is invalid

D. Dense layer cannot follow Conv2D without flattening

Solution

1. Step 1: Check layer sequence

   Conv2D outputs 4D tensor, Dense expects 2D input, so flattening is needed before Dense.

2. Step 2: Validate other options

   Input shape is valid for images, 'relu' is a valid activation, kernel size 3 is allowed.

3. Final Answer:

   Dense layer cannot follow Conv2D without flattening -> Option D

4. Quick Check:

   Dense after Conv2D needs flattening [OK]

Hint: Dense layers need flat input, add Flatten after Conv2D [OK]

Common Mistakes:

• Ignoring tensor shape mismatch
• Thinking kernel size must be 1
• Misunderstanding activation functions

5. You want to train a simple segmentation model in TensorFlow. Which data do you need to provide during training?

hard

A. Only images without labels

B. Images and image-level class labels

C. Images and their pixel-level masks

D. Random noise images

Solution

1. Step 1: Identify training data for segmentation

   Segmentation requires images and masks labeling each pixel's class to learn pixel-wise predictions.

2. Step 2: Compare with other data types

   Image-level labels are for classification, no labels means no supervision, noise images are irrelevant.

3. Final Answer:

   Images and their pixel-level masks -> Option C

4. Quick Check:

   Training segmentation = images + pixel masks [OK]

Hint: Segmentation training needs pixel masks, not just labels [OK]

Common Mistakes:

• Using only image-level labels
• Training without masks
• Confusing segmentation with classification data