Image segmentation basics in TensorFlow - Model Pipeline Trace

Model Pipeline - Image segmentation basics

This pipeline takes images and teaches a model to color each pixel to show different objects. It helps computers understand pictures like how we see separate things.

Data Flow - 5 Stages

1Input Images

1000 images x 128 x 128 x 3→Raw color images loaded→1000 images x 128 x 128 x 3

A 128x128 photo with red, green, blue colors

↓

2Preprocessing

1000 images x 128 x 128 x 3→Normalize pixel values to 0-1 range→1000 images x 128 x 128 x 3

Pixel value 255 becomes 1.0, 0 stays 0.0

↓

3Label Masks

1000 images x 128 x 128→Load pixel-wise labels for objects→1000 images x 128 x 128

Each pixel labeled 0=background, 1=cat, 2=dog

↓

4Train/Test Split

1000 images x 128 x 128 x 3 and 1000 masks x 128 x 128→Split data into 800 train and 200 test samples→800 train images x 128 x 128 x 3, 200 test images x 128 x 128 x 3; 800 train masks x 128 x 128, 200 test masks x 128 x 128

Training set has 800 photos and masks

↓

5Model Training

800 train images x 128 x 128 x 3 and masks→Train U-Net model to predict mask from image→Trained model

Model learns to color pixels as cat or dog

Training Trace - Epoch by Epoch

Epoch 1: *********
Epoch 5: *****
Epoch 10: ***
Epoch 15: **
Epoch 20: *
(Loss decreases over epochs)

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.60	Model starts learning basic shapes
5	0.45	0.78	Model improves on pixel classification
10	0.30	0.85	Model segments objects more clearly
15	0.22	0.90	Model predictions become sharper
20	0.18	0.92	Model converges with good segmentation

Prediction Trace - 6 Layers

Layer 1: Input Image

Layer 2: Encoder Layers

Layer 3: Bottleneck

Layer 4: Decoder Layers

Layer 5: Output Layer (Softmax)

Layer 6: Final Prediction

Model Quiz - 3 Questions

What does the model output in image segmentation?

A A mask labeling each pixel with a class

B A single label for the whole image

C A resized version of the input image

D A list of object names detected

Key Insight

Image segmentation models learn to assign a class to every pixel by gradually improving predictions through training. Normalizing inputs and using encoder-decoder structures help the model understand and recreate detailed object shapes.

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