Why visual AI extends beyond classification in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained image classification model in TensorFlow.

TensorFlow

import tensorflow as tf
model = tf.keras.applications.[1](weights='imagenet')

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

AResNet50

BRandomForest

CLinearRegression

DKMeans

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing models not related to image classification like LinearRegression.

ResNet50 is a popular pre-trained model for image classification available in TensorFlow Keras applications.

2fill in blank

medium

Complete the code to preprocess an image for the ResNet50 model.

TensorFlow

from tensorflow.keras.applications.resnet50 import preprocess_input
img = tf.keras.utils.load_img('image.jpg', target_size=(224, 224))
img_array = tf.keras.utils.img_to_array(img)
img_array = tf.expand_dims(img_array, axis=0)
processed_img = [1](img_array)

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

Aresize

Bpreprocess_input

Cnormalize

Ddecode_predictions

Attempts:

3 left

💡 Hint

Common Mistakes

Using decode_predictions instead of preprocess_input for preprocessing.

The preprocess_input function prepares the image array correctly for ResNet50 model input.

3fill in blank

hard

Fix the error in the code to get predictions from the model and decode them.

TensorFlow

preds = model.predict(processed_img)
results = tf.keras.applications.resnet50.[1](preds, top=3)

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

Aload_img

Bpreprocess_input

Cpredict_classes

Ddecode_predictions

Attempts:

3 left

💡 Hint

Common Mistakes

Using preprocess_input instead of decode_predictions after prediction.

decode_predictions converts model output into human-readable labels with probabilities.

4fill in blank

hard

Fill both blanks to create a simple image segmentation model using TensorFlow Keras.

TensorFlow

from tensorflow.keras import layers, models
inputs = layers.Input(shape=(128, 128, 3))
x = layers.Conv2D(32, (3, 3), activation='relu', padding='same')([1])
x = layers.Conv2D(1, (1, 1), activation='sigmoid', padding='same')([2])
model = models.Model(inputs=inputs, outputs=x)

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

Ainputs

Bx

Coutputs

Dmodel

Attempts:

3 left

💡 Hint

Common Mistakes

Passing wrong variables like 'outputs' or 'model' to layers.

The first Conv2D layer takes inputs as input; the second Conv2D layer takes the output of the first layer 'x'.

5fill in blank

hard

Fill all three blanks to compute accuracy and loss for a classification model in TensorFlow.

TensorFlow

model.compile(optimizer='adam', loss=[1], metrics=[[2]])
history = model.fit(train_data, train_labels, epochs=5)
final_acc = history.history[[3]][-1]

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

A'categorical_crossentropy'

B'accuracy'

D'loss'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'loss' key to get accuracy or wrong loss function.

Loss is 'categorical_crossentropy', metric is 'accuracy', and final accuracy is accessed by 'accuracy' key in history.

Practice

1. Which of the following best explains why visual AI goes beyond simple image classification?

easy

A. Because it includes tasks like detecting objects and segmenting images for detailed understanding.

B. Because classification is the only task needed for image understanding.

C. Because visual AI only works with black and white images.

D. Because it ignores the content inside images.

Solution

1. Step 1: Understand the scope of visual AI

   Visual AI includes many tasks beyond classification, such as object detection and segmentation, which provide more detailed information about images.

2. Step 2: Compare options

   Because it includes tasks like detecting objects and segmenting images for detailed understanding. correctly states that visual AI includes these tasks, while others are incorrect or too narrow.

3. Final Answer:

   Because it includes tasks like detecting objects and segmenting images for detailed understanding. -> Option A

4. Quick Check:

   Visual AI = More than classification [OK]

Hint: Visual AI means detailed image understanding, not just labels [OK]

Common Mistakes:

• Thinking classification covers all visual AI tasks
• Ignoring object detection and segmentation
• Confusing image color with AI capability

2. Which TensorFlow function is commonly used to build a model for image segmentation tasks?

easy

A. tf.keras.Sequential()

B. tf.keras.Model()

C. tf.keras.layers.Conv2D()

D. tf.data.Dataset()

Solution

1. Step 1: Identify model building functions

   tf.keras.Model() allows building complex models like those needed for image segmentation, supporting multiple inputs and outputs.

2. Step 2: Compare other options

   tf.keras.Sequential() is simpler and less flexible, Conv2D is a layer, and tf.data.Dataset is for data input pipelines.

3. Final Answer:

   tf.keras.Model() -> Option B

4. Quick Check:

   Use tf.keras.Model for flexible segmentation models [OK]

Hint: Use tf.keras.Model for complex image tasks like segmentation [OK]

Common Mistakes:

• Confusing layers with model constructors
• Using Sequential for multi-output models
• Mixing data pipeline functions with model building

3. Given this TensorFlow code snippet for object detection, what will be the shape of the output tensor?

import tensorflow as tf
model = tf.keras.Sequential([
  tf.keras.layers.Conv2D(16, 3, activation='relu', input_shape=(64, 64, 3)),
  tf.keras.layers.Flatten(),
  tf.keras.layers.Dense(4)  # outputs bounding box coordinates
])
output = model(tf.random.uniform([1, 64, 64, 3]))
print(output.shape)

medium

A. (1, 4)

B. (64, 64, 16)

C. (1, 64, 64, 16)

D. (4,)

Solution

1. Step 1: Analyze model layers and output

   The model input is (64, 64, 3). Conv2D outputs (64, 64, 16). Flatten converts this to a vector, then Dense(4) outputs a vector of size 4.

2. Step 2: Check batch dimension

   Input batch size is 1, so output shape is (1, 4).

3. Final Answer:

   (1, 4) -> Option A

4. Quick Check:

   Output shape = (batch_size, 4) [OK]

Hint: Dense(4) outputs shape (batch_size, 4) after flatten [OK]

Common Mistakes:

• Confusing Conv2D output shape with final output
• Ignoring batch dimension
• Assuming output shape matches input image size

4. This TensorFlow code aims to perform image segmentation but has an error. What is the problem?

import tensorflow as tf
inputs = tf.keras.Input(shape=(128, 128, 3))
x = tf.keras.layers.Conv2D(32, 3, activation='relu')(inputs)
x = tf.keras.layers.Dense(1, activation='sigmoid')(x)
model = tf.keras.Model(inputs, x)

medium

A. Missing activation function in Conv2D layer.

B. Input shape is incorrect for image data.

C. Model lacks an output layer.

D. Dense layer cannot be applied directly to 4D tensor from Conv2D.

Solution

1. Step 1: Understand layer input/output shapes

   Conv2D outputs a 4D tensor (batch, height, width, channels). Dense expects 2D input (batch, features).

2. Step 2: Identify the error

   Applying Dense directly to Conv2D output causes shape mismatch error.

3. Final Answer:

   Dense layer cannot be applied directly to 4D tensor from Conv2D. -> Option D

4. Quick Check:

   Dense needs 2D input, Conv2D outputs 4D [OK]

Hint: Dense layers need flat input, not Conv2D 4D output [OK]

Common Mistakes:

• Assuming Dense works on 4D tensors
• Ignoring tensor shape requirements
• Thinking activation missing causes error

5. You want to build a TensorFlow model that not only classifies images but also detects multiple objects and segments them. Which approach best fits this goal?

hard

A. Use only a classification model and infer objects from class labels.

B. Train separate models for classification, detection, and segmentation and use them independently.

C. Use a single model with multiple outputs: one for classification, one for bounding boxes, and one for segmentation masks.

D. Use a simple Dense network with one output layer.

Solution

1. Step 1: Understand multi-task learning

   A single model with multiple outputs can learn classification, detection, and segmentation together, sharing features efficiently.

2. Step 2: Compare alternatives

   Separate models increase complexity and latency; classification-only models lack detection and segmentation; simple Dense networks cannot handle images well.

3. Final Answer:

   Use a single model with multiple outputs: one for classification, one for bounding boxes, and one for segmentation masks. -> Option C

4. Quick Check:

   Multi-output model fits combined visual AI tasks [OK]

Hint: Multi-output models handle classification, detection, segmentation together [OK]

Common Mistakes:

• Thinking separate models are always better
• Ignoring need for segmentation masks
• Using simple Dense layers for images