Training history and visualization in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the final training accuracy after 3 epochs?

Consider this TensorFlow training code snippet. What is the final training accuracy printed after training for 3 epochs?

TensorFlow

import tensorflow as tf
from tensorflow.keras import layers, models

model = models.Sequential([
    layers.Dense(10, activation='relu', input_shape=(5,)),
    layers.Dense(2, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

import numpy as np
x_train = np.random.random((100, 5))
y_train = np.random.randint(0, 2, 100)

history = model.fit(x_train, y_train, epochs=3, verbose=0)

final_acc = history.history['accuracy'][-1]
print(round(final_acc, 2))

A 0.75

B 0.99

C 0.50

D 0.85

💡 Hint

Look at the last value in the 'accuracy' list from the history object.

The model trains for 3 epochs and the accuracy improves from around 0.5 to about 0.85 by the last epoch.

🧠 Conceptual

intermediate

What does the 'history.history' dictionary contain?

After training a TensorFlow model, the 'history' object has an attribute 'history'. What does this dictionary store?

A The compiled model configuration

B The model's weights after training

C Lists of metric values and loss for each epoch during training

D The training dataset used for fitting the model

💡 Hint

Think about what changes after each epoch during training.

The 'history.history' dictionary stores lists of values for each metric and loss recorded at the end of every epoch.

❓ Metrics

advanced

Which metric is best to monitor for classification accuracy during training?

You want to track how well your classification model predicts correct labels during training. Which metric should you monitor?

A accuracy

B mean_squared_error

C categorical_crossentropy

D mean_absolute_error

💡 Hint

Accuracy measures correct predictions as a percentage.

Accuracy directly measures the proportion of correct predictions, making it ideal for classification tasks.

🔧 Debug

advanced

Why does this training history plot show a flat line?

You run this code to plot training accuracy but the graph is a flat line at 1.0. What is the likely cause? import matplotlib.pyplot as plt plt.plot(history.history['accuracy']) plt.xlabel('Epoch') plt.ylabel('Accuracy') plt.show()

TensorFlow

import tensorflow as tf
from tensorflow.keras import layers, models
import numpy as np

model = models.Sequential([
    layers.Dense(10, activation='relu', input_shape=(5,)),
    layers.Dense(2, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

x_train = np.random.random((100, 5))
y_train = np.zeros(100, dtype=int)  # All labels are zero

history = model.fit(x_train, y_train, epochs=5, verbose=0)

import matplotlib.pyplot as plt
plt.plot(history.history['accuracy'])
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.show()

A The model did not compile correctly

B The training labels have no variation, so accuracy stays constant

C The plot command is missing plt.show()

D The accuracy metric is not supported for this model

💡 Hint

Check the training labels and their diversity.

Since all labels are zero, the model can easily predict the same class and accuracy remains constant at 1.0.

❓ Model Choice

expert

Which model architecture is best for visualizing training history of a time series prediction?

You want to train a model on time series data and visualize its training loss and accuracy. Which model architecture is most suitable?

A A recurrent neural network (RNN) with LSTM layers

B A simple dense neural network with one hidden layer

C A convolutional neural network (CNN) designed for image data

D A linear regression model without epochs

💡 Hint

Time series data has order and sequence information.

RNNs with LSTM layers are designed to handle sequential data like time series and can be trained over epochs to visualize training history.