This short introduction uses Tensorflow Keras to:

• Build a neural network that classifies images.
• Train this neural network.
• And, finally, evaluate the accuracy of the model.

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in 

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt

import hashlib  # Standard Python library for creating cryptographic hashes (one-way fingerprints of data)

# 👇️ disable tensorflow warnings
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

import tensorflow as tf
print("TensorFlow version:", tf.__version__)

To Check GPU Availability in Tensorflow

gpus = tf.config.experimental.list_physical_devices('GPU')
for gpu in gpus:
    print("Name:", gpu.name, "  Type:", gpu.device_type)

Listing Devices including GPU's with Tensorflow

from tensorflow.python.client import device_lib

devices = device_lib.list_local_devices()

for d in devices:
    if d.device_type == "GPU":
        desc = d.physical_device_desc
        correct_compute = float(desc.split("compute capability:")[1])


print(devices)

Task 1: Write the compute capability for Jetson Orin Nano

# TODO: Fill in the compute capability of the GPU
compute_capability = None # replace None with your answer


# The following code is only to check your answer
correct_compute_hash = '8719c8b9d63c644df3a5b778698dbdaa3c3f1b746f3cbb41b28a5f79a8989229'
assert hashlib.sha256(str(compute_capability).encode()).hexdigest() == correct_compute_hash, "❌ Incorrect. Check the GPU info from the previous cell."
print("✅ Correct! Compute capability is", compute_capability)

To Check GPU in Tensorflow

tf.config.list_physical_devices('GPU')

Import the Fashion MNIST dataset

This guide uses the Fashion MNIST dataset which contains 70,000 grayscale images in 10 categories. The images show individual articles of clothing at low resolution (28 by 28 pixels)

Fashion MNIST is intended as a drop-in replacement for the classic MNIST dataset—often used as the "Hello, World" of machine learning programs for computer vision. The MNIST dataset contains images of handwritten digits (0, 1, 2, etc.) in a format identical to that of the articles of clothing you'll use here.

This guide uses Fashion MNIST for variety, and because it's a slightly more challenging problem than regular MNIST. Both datasets are relatively small and are used to verify that an algorithm works as expected. They're good starting points to test and debug code.

Here, 60,000 images are used to train the network and 10,000 images to evaluate how accurately the network learned to classify images. You can access the Fashion MNIST directly from TensorFlow. Import and load the Fashion MNIST data directly from TensorFlow:

fashion_mnist = tf.keras.datasets.fashion_mnist

(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()

Each image is mapped to a single label. Since the class names are not included with the dataset, store them here to use later when plotting the images:

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

Explore the data

Let's explore the format of the dataset before training the model. The following shows there are 60,000 images in the training set, with each image represented as 28 x 28 pixels:

train_images.shape

len(train_labels)

test_images.shape

Each label is an integer between 0 and 9:

train_labels

Task 2: How many images in Fashion MNIST dataset

# TODO: Fill in the number of images in Fashion MNIST
number_images_FashionMNIST = None # replace None with your answer


# The following code is only to check your answer
correct_compute_hash = '265f10e1bf87701b7aa597c197b6a25b0984777f3443a289d7a92aedd31fddcf'
assert hashlib.sha256(str(number_images_FashionMNIST).encode()).hexdigest() == correct_compute_hash, "❌ Incorrect. Check the number of images info from the previous cells."
print("✅ Correct! Total number of images in Fashion MNIST is ", number_images_FashionMNIST)

Preprocess the data

The data must be preprocessed before training the network. If you inspect the first image in the training set, you will see that the pixel values fall in the range of 0 to 255:

plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()

Scale these values to a range of 0 to 1 before feeding them to the neural network model. To do so, divide the values by 255. It's important that the training set and the testing set be preprocessed in the same way:

train_images = train_images / 255.0

test_images = test_images / 255.0

To verify that the data is in the correct format and that you're ready to build and train the network, let's display the first 25 images from the training set and display the class name below each image.

plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])
plt.show()

Build a machine learning model

Architecture of the Network is :-

1. Input layer for 28x28 images in MNiST dataset

2. Dense layer with 128 neurons and ReLU activation function

3. Output layer with 10 neurons for classification of input images as one of ten digits(0 to 9)

model = tf.keras.Sequential([
    tf.keras.Input(shape=(28, 28)),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10)
])
model.summary()

Sequential is useful for stacking layers where each layer has one input tensor and one output tensor. Layers are functions with a known mathematical structure that can be reused and have trainable variables. Most TensorFlow models are composed of layers. This model uses the Flatten, Dense, and Dropout layers.

The first layer in this network, tf.keras.layers.Flatten, transforms the format of the images from a two-dimensional array (of 28 by 28 pixels) to a one-dimensional array (of 28 * 28 = 784 pixels). Think of this layer as unstacking rows of pixels in the image and lining them up. This layer has no parameters to learn; it only reformats the data.

After the pixels are flattened, the network consists of a sequence of two tf.keras.layers.Dense layers. These are densely connected, or fully connected, neural layers. The first Dense layer has 128 nodes (or neurons). The second (and last) layer returns a logits array with length of 10. Each node contains a score that indicates the current image belongs to one of the 10 classes.

Task 3: How many parameters in the hidden layer

# TODO: Enter the total number of parameters in the hidden layer of the previous model:
number_hidden_parameters = None # replace None with your answer


# The following code is only to check your answer
correct_hash = 'ced6f96cd7e1da5334fc3d780adf50083556060c95d04ceea32147bce28058de'
assert hashlib.sha256(str(number_hidden_parameters).encode()).hexdigest() == correct_hash, "❌ Incorrect. Check the number of images info from the previous cells."
print("✅ Correct! Total number of images in Fashion MNIST is ", number_hidden_parameters)

For each example, the model returns a vector of logits or log-odds scores, one for each class.

predictions = model(train_images[:1]).numpy()
predictions

The tf.nn.softmax function converts these logits to probabilities for each class:

tf.nn.softmax(predictions).numpy()

Compile the model

Before the model is ready for training, it needs a few more settings. These are added during the model's compile step:

• Optimizer —This is how the model is updated based on the data it sees and its loss function.
• Loss function —This measures how accurate the model is during training. You want to minimize this function to "steer" the model in the right direction.
• Metrics —Used to monitor the training and testing steps. The following example uses accuracy, the fraction of the images that are correctly classified.

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

Train the model

Training the neural network model requires the following steps:

1. Feed the training data to the model. In this example, the training data is in the train_images and train_labels arrays.
2. The model learns to associate images and labels.
3. You ask the model to make predictions about a test set—in this example, the test_images array.
4. Verify that the predictions match the labels from the test_labels array.

Feed the model

To start training, call the model.fit method—so called because it "fits" the model to the training data:

model.fit(train_images, train_labels, epochs=10)

As the model trains, the loss and accuracy metrics are displayed. This model reaches an accuracy of about 0.91 (or 91%) on the training data.

Evaluate accuracy

Next, compare how the model performs on the test dataset:

test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)

print('\nTest accuracy:', test_acc)

It turns out that the accuracy on the test dataset is a little less than the accuracy on the training dataset. This gap between training accuracy and test accuracy represents overfitting. Overfitting happens when a machine learning model performs worse on new, previously unseen inputs than it does on the training data. An overfitted model "memorizes" the noise and details in the training dataset to a point where it negatively impacts the performance of the model on the new data.

Make predictions

With the model trained, you can use it to make predictions about some images. Attach a softmax layer to convert the model's linear outputs—logits—to probabilities, which should be easier to interpret.

probability_model = tf.keras.Sequential([model, 
                                         tf.keras.layers.Softmax()])

predictions = probability_model.predict(test_images)

Here, the model has predicted the label for each image in the testing set. Let's take a look at the first prediction:

predictions[0]

A prediction is an array of 10 numbers. They represent the model's "confidence" that the image corresponds to each of the 10 different articles of clothing. You can see which label has the highest confidence value:

np.argmax(predictions[0])

So, the model is most confident that this image is an ankle boot, or class_names[9].. Examining the test label shows that this classification is correct:

test_labels[0]

Define functions to graph the full set of 10 class predictions.

def plot_image(i, predictions_array, true_label, img):
  true_label, img = true_label[i], img[i]
  plt.grid(False)
  plt.xticks([])
  plt.yticks([])

  plt.imshow(img, cmap=plt.cm.binary)

  predicted_label = np.argmax(predictions_array)
  if predicted_label == true_label:
    color = 'blue'
  else:
    color = 'red'

  plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
                                100*np.max(predictions_array),
                                class_names[true_label]),
                                color=color)

def plot_value_array(i, predictions_array, true_label):
  true_label = true_label[i]
  plt.grid(False)
  plt.xticks(range(10))
  plt.yticks([])
  thisplot = plt.bar(range(10), predictions_array, color="#777777")
  plt.ylim([0, 1])
  predicted_label = np.argmax(predictions_array)

  thisplot[predicted_label].set_color('red')
  thisplot[true_label].set_color('blue')

Verify predictions

With the model trained, you can use it to make predictions about some images.

Let's look at the 0th image, predictions, and prediction array. Correct prediction labels are blue and incorrect prediction labels are red. The number gives the percentage (out of 100) for the predicted label.

i = 0
plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1,2,2)
plot_value_array(i, predictions[i],  test_labels)
plt.show()

i = 12
plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1,2,2)
plot_value_array(i, predictions[i],  test_labels)
plt.show()

# Plot the first X test images, their predicted labels, and the true labels.
# Color correct predictions in blue and incorrect predictions in red.
num_rows = 8
num_cols = 3
num_images = num_rows*num_cols
plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_images):
  plt.subplot(num_rows, 2*num_cols, 2*i+1)
  plot_image(i, predictions[i], test_labels, test_images)
  plt.subplot(num_rows, 2*num_cols, 2*i+2)
  plot_value_array(i, predictions[i], test_labels)
plt.tight_layout()
plt.show()