Predict Vehicle Fuel Economy Using a Deep Neural Network

In this tutorial, we will use Tensorflow 2.0 with Keras to build a deep neural network that will enable us to predict a vehicle’s fuel economy (in miles per gallon) from eight different attributes: 

  1. Cylinders
  2. Displacement
  3. Horsepower
  4. Weight
  5. Acceleration 
  6. Model year 
  7. Origin
  8. Car name

We will use the Auto MPG Data Set at the UCI Machine Learning Repository.

Prerequisites

  • You have TensorFlow 2 Installed.
    • Windows 10 Users, see this post.
    • If you want to use GPU support for your TensorFlow installation, you will need to follow these steps. If you have trouble following those steps, you can follow these steps (note that the steps change quite frequently, but the overall process remains relatively the same).

Directions

Open up a new Python program (in your favorite text editor or Python IDE) and write the following code. I’m going to name the program vehicle_fuel_economy.py. I’ll explain the code later in this tutorial.

# Project: Predict Vehicle Fuel Economy Using a Deep Neural Network
# Author: Addison Sears-Collins
# Date created: November 3, 2020

import pandas as pd # Used for data analysis
import pathlib # An object-oriented interface to the filesystem
import matplotlib.pyplot as plt # Handles the creation of plots
import seaborn as sns # Data visualization library
import tensorflow as tf # Machine learning library
from tensorflow import keras # Library for neural networks
from tensorflow.keras import layers # Handles the layers of the neural network

def main():

  # Set the data path for the Auto-Mpg data set from the UCI Machine Learning Repository
  datasetPath = keras.utils.get_file("auto-mpg.data", "https://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")

  # Set the column names for the data set
  columnNames = ['MPG', 'Cylinders','Displacement','Horsepower','Weight',
               'Acceleration','Model Year','Origin']

  # Import the data set
  originalData = pd.read_csv(datasetPath, names=columnNames, na_values = "?", 
                           comment='\t', sep=" ", skipinitialspace=True)
						 
  # Check the data set
  # print("Original Data Set Excerpt")
  # print(originalData.head())
  # print()

  # Generate a copy of the data set
  data = originalData.copy()

  # Count how many NAs each data attribute has
  # print("Number of NAs in the data set")
  # print(data.isna().sum())
  # print()

  # Now, let's remove the NAs from the data set
  data = data.dropna()

  # Perform one-hot encoding on the Origin attribute 
  # since it is a categorical variable
  origin = data.pop('Origin') # Return item and drop from frame
  data['USA'] = (origin == 1) * 1.0
  data['Europe'] = (origin == 2) * 1.0
  data['Japan'] = (origin == 3) * 1.0

  # Generate a training data set (80% of the data) and a testing set (20% of the data)
  trainingData = data.sample(frac = 0.8, random_state = 0)

  # Generate a testing data set
  testingData = data.drop(trainingData.index)

  # Separate the attributes from the label in both the testing
  # and training data. The label is the thing we are trying
  # to predit (i.e. miles per gallon 'MPG')
  trainingLabelData = trainingData.pop('MPG')
  testingLabelData = testingData.pop('MPG')
  
  # Normalize the data
  normalizedTrainingData = normalize(trainingData)
  normalizedTestingData = normalize(testingData)
  #print(normalizedTrainingData.head()) 
  
  # Generate the neural network
  neuralNet = generateNeuralNetwork(trainingData)
  
  # See a summary of the neural network
  # The first layer has 640 parameters 
    #(9 input values * 64 neurons) + 64 bias values
  # The second layer has 4160 parameters 
    #(64 input values * 64 neurons) + 64 bias values
  # The output layer has 65 parameters 
    #(64 input values * 1 neuron) + 1 bias value
  #print(neuralNet.summary())
  
  EPOCHS = 1000
  
  # Train the model for a fixed number of epochs
  # history.history attribute is returned from the fit() function.
  # history.history is a record of training loss values and 
  # metrics values at successive epochs, as well as validation 
  # loss values and validation metrics values.
  history = neuralNet.fit(
    x = normalizedTrainingData, 
    y = trainingLabelData,
    epochs = EPOCHS, 
    validation_split = 0.2, 
    verbose = 0,
    callbacks = [PrintDot()]
  )   
  
  # Plot the neural network metrics (Training error and validation error)
  # Training error is the error when the trained neural network is 
  #   run on the training data.
  # Validation error is used to minimize overfitting. It indicates how
  #   well the data fits on data it hasn't been trained on.
  #plotNeuralNetMetrics(history)
  
  # Generate another neural network so that we can use early stopping
  neuralNet2 = generateNeuralNetwork(trainingData)
  
  # We want to stop training the model when the 
  # validation error stops improving.
  # monitor indicates the quantity we want to monitor.
  # patience indicates the number of epochs with no improvement after which
  # training will terminate.
  earlyStopping = keras.callbacks.EarlyStopping(monitor = 'val_loss', patience = 10)

  history2 = neuralNet2.fit(
    x = normalizedTrainingData, 
    y = trainingLabelData,
    epochs = EPOCHS, 
    validation_split = 0.2, 
    verbose = 0,
    callbacks = [earlyStopping, PrintDot()]
  )    

  # Plot metrics
  #plotNeuralNetMetrics(history2) 
  
  # Return the loss value and metrics values for the model in test mode
  # The mean absolute error for the predictions should 
  # stabilize around 2 miles per gallon  
  loss, meanAbsoluteError, meanSquaredError = neuralNet2.evaluate(
    x = normalizedTestingData,
	y = testingLabelData,
    verbose = 0
  )
  
  #print(f'\nMean Absolute Error on Test Data Set = {meanAbsoluteError} miles per gallon')
  
  # Make fuel economy predictions by deploying the trained neural network on the 
  # test data set (data that is brand new for the trained neural network).
  testingDataPredictions = neuralNet2.predict(normalizedTestingData).flatten()
  
  # Plot the predicted MPG vs. the true MPG
  # testingLabelData are the true MPG values
  # testingDataPredictions are the predicted MPG values
  #plotTestingDataPredictions(testingLabelData, testingDataPredictions)
  
  # Plot the prediction error distribution
  #plotPredictionError(testingLabelData, testingDataPredictions)
  
  # Save the neural network in Hierarchical Data Format version 5 (HDF5) format
  neuralNet2.save('fuel_economy_prediction_nnet.h5')
  
  # Import the saved model
  neuralNet3 = keras.models.load_model('fuel_economy_prediction_nnet.h5')
  print("\n\nNeural network has loaded successfully...\n")
  
  # Show neural network parameters
  print(neuralNet3.summary())
  
  # Make a prediction using the saved model we just imported
  print("\nMaking predictions...")
  testingDataPredictionsNN3 = neuralNet3.predict(normalizedTestingData).flatten()
  
  # Show Predicted MPG vs. Actual MPG
  plotTestingDataPredictions(testingLabelData, testingDataPredictionsNN3) 
  
# Generate the neural network
def generateNeuralNetwork(trainingData):
  # A Sequential model is a stack of layers where each layer is
  # single-input, single-output
  # This network below has 3 layers.
  neuralNet = keras.Sequential([
  
    # Each neuron in a layer recieves input from all the 
    # neurons in the previous layer (Densely connected)
    # Use the ReLU activation function. This function transforms the input
	# into a node (i.e. summed weighted input) into output	
    # The first layer needs to know the number of attributes (keys) in the data set.
	# This first and second layers have 64 nodes.
    layers.Dense(64, activation=tf.nn.relu, input_shape=[len(trainingData.keys())]),
    layers.Dense(64, activation=tf.nn.relu),
    layers.Dense(1) # This output layer is a single, continuous value (i.e. Miles per gallon)
  ])

  # Penalize the update of the neural network parameters that are causing
  # the cost function to have large oscillations by using a moving average
  # of the square of the gradients and dibiding the gradient by the root of this
  # average. Reduces the step size for large gradients and increases 
  # the step size for small gradients.
  # The input into this function is the learning rate.
  optimizer = keras.optimizers.RMSprop(0.001)
 
  # Set the configurations for the model to get it ready for training
  neuralNet.compile(loss = 'mean_squared_error',
                optimizer = optimizer,
                metrics = ['mean_absolute_error', 'mean_squared_error'])
  return neuralNet
    
# Normalize the data set using the mean and standard deviation 
def normalize(data):
  statistics = data.describe()
  statistics = statistics.transpose()
  return(data - statistics['mean']) / statistics['std']

# Plot metrics for the neural network  
def plotNeuralNetMetrics(history):
  neuralNetMetrics = pd.DataFrame(history.history)
  neuralNetMetrics['epoch'] = history.epoch
  
  plt.figure()
  plt.xlabel('Epoch')
  plt.ylabel('Mean Abs Error [MPG]')
  plt.plot(neuralNetMetrics['epoch'], 
           neuralNetMetrics['mean_absolute_error'],
           label='Train Error')
  plt.plot(neuralNetMetrics['epoch'], 
           neuralNetMetrics['val_mean_absolute_error'],
           label = 'Val Error')
  plt.ylim([0,5])
  plt.legend()
  
  plt.figure()
  plt.xlabel('Epoch')
  plt.ylabel('Mean Square Error [$MPG^2$]')
  plt.plot(neuralNetMetrics['epoch'], 
           neuralNetMetrics['mean_squared_error'],
           label='Train Error')
  plt.plot(neuralNetMetrics['epoch'], 
           neuralNetMetrics['val_mean_squared_error'],
           label = 'Val Error')
  plt.ylim([0,20])
  plt.legend()
  plt.show()
  
# Plot prediction error
def plotPredictionError(testingLabelData, testingDataPredictions):

  # Error = Predicted - Actual
  error = testingDataPredictions - testingLabelData
  
  plt.hist(error, bins = 50)
  plt.xlim([-10,10])
  plt.xlabel("Predicted MPG - Actual MPG")
  _ = plt.ylabel("Count")
  plt.show()

# Plot predictions vs. true values
def plotTestingDataPredictions(testingLabelData, testingDataPredictions):

  # Plot the data points (x, y)
  plt.scatter(testingLabelData, testingDataPredictions)
  
  # Label the axes
  plt.xlabel('True Values (Miles per gallon)')
  plt.ylabel('Predicted Values (Miles per gallon)')

  # Plot a line between (0,0) and (50,50) 
  point1 = [0, 0]
  point2 = [50, 50]
  xValues = [point1[0], point2[0]] 
  yValues = [point1[1], point2[1]]
  plt.plot(xValues, yValues) 
  
  # Set the x and y axes limits
  plt.xlim(0, 50)
  plt.ylim(0, 50)

  # x and y axes are equal in displayed dimensions
  plt.gca().set_aspect('equal', adjustable='box')
  
  # Show the plot
  plt.show()
  
  
# Show the training process by printing a period for each epoch that completes
class PrintDot(keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs):
    if epoch % 100 == 0: print('')
    print('.', end='')
	
main()

Save the Python program.

If you run your Python programs using Anaconda, open the Anaconda prompt.

If you like to run your programs in a virtual environment, activate the virtual environment. I have a virtual environment named tf_2.

conda activate tf_2

Navigate to the folder where you saved the Python program.

cd [path to folder]

For example,

cd C:\MyFiles

Install any libraries that you need. I didn’t have some of the libraries in the “import” section of my code installed, so I’ll install them now.

pip install pandas
pip install seaborn

To run the code, type:

python vehicle_fuel_economy.py

If you’re using a GPU with Tensorflow, and you’re getting error messages about libraries missing, go to this folder C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1\bin, and you can search on the Internet for the missing dll files. Download them, and then put them in that bin folder.

Code Output

In this section, I will pull out snippets of the code and show you the resulting output when you uncomment those lines.

  # Check the data set
  print("Original Data Set Excerpt")
  print(originalData.head())
  print()
1_original_datasetJPG
  # Count how many NAs each data attribute has
  print("Number of NAs in the data set")
  print(data.isna().sum())
  print()
2-number-of-nasJPG
  # See a summary of the neural network
  # The first layer has 640 parameters 
    #(9 input values * 64 neurons) + 64 bias values
  # The second layer has 4160 parameters 
    #(64 input values * 64 neurons) + 64 bias values
  # The output layer has 65 parameters 
    #(64 input values * 1 neuron) + 1 bias value
  print(neuralNet.summary())

3-output-of-neural-net-summaryJPG
  # Plot the neural network metrics (Training error and validation error)
  # Training error is the error when the trained neural network is 
  #   run on the training data.
  # Validation error is used to minimize overfitting. It indicates how
  #   well the data fits on data it hasn't been trained on.
  plotNeuralNetMetrics(history)

4-mean-absolute-errorJPG
5-mean-squared-errorJPG
  # Plot metrics
  plotNeuralNetMetrics(history2) 
6-error-with-early-stoppingJPG
print(f'\nMean Absolute Error on Test Data Set = {meanAbsoluteError} miles per gallon') 
7-mae-test-data-setJPG
  # Plot the predicted MPG vs. the true MPG
  # testingLabelData are the true MPG values
  # testingDataPredictions are the predicted MPG values
  plotTestingDataPredictions(testingLabelData, testingDataPredictions)
8-predicted-vs-trueJPG
  # Plot the prediction error distribution
  plotPredictionError(testingLabelData, testingDataPredictions)
9-prediction-error-frequencyJPG
  # Save the neural network in Hierarchical Data Format version 5 (HDF5) format
  neuralNet2.save('fuel_economy_prediction_nnet.h5')
  
  # Import the saved model
  neuralNet3 = keras.models.load_model('fuel_economy_prediction_nnet.h5')
10-loading-and-saving-a-neural-networkJPG

References

Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.

What is Deep Learning?

In previous posts, I’ve talked a lot about deep learning.

However, I have never actually explained, in a concise way, what deep learning is, so here we go.

Deep learning is a technique for teaching a computer how to make predictions based on a set of inputs.

Input Data —–> Deep Learning Algorithm (i.e. Process) —–> Output Data

To make predictions (i.e. the “Process” part of the line above), deep learning uses deep neural networks. A deep neural network is a computer-based, simplified representation of neurons in the brain. It is computer science’s attempt to get a computer to process information just like real neurons in our brains do.

neural-network

Deep neural networks are well suited for complex applications like computer vision, natural language processing, and machine translation where you want to draw useful information from nonlinear and unstructured data such as images, audio, or text.

Real-Time Object Recognition Using a Webcam and Deep Learning

*** This tutorial is two years old and may no longer work properly. You can find an updated tutorial for object recognition at this link***

In this tutorial, we will develop a program that can recognize objects in a real-time video stream on a built-in laptop webcam using deep learning.

object-detection-recognition-video-demo

Object recognition involves two main tasks:

  1. Object Detection (Where are the objects?): Locate objects in a photo or video frame
  2. Image Classification (What are the objects?): Predict the type of each object in a photo or video frame

Humans can do both tasks effortlessly, but computers cannot.

Computers require a lot of processing power to take full advantage of the state-of-the-art algorithms that enable object recognition in real time. However, in recent years, the technology has matured, and real-time object recognition is now possible with only a laptop computer and a webcam.

Real-time object recognition systems are currently being used in a number of real-world applications, including the following:

  • Self-driving cars: detection of pedestrians, cars, traffic lights, bicycles, motorcycles, trees, sidewalks, etc.
  • Surveillance: catching thieves, counting people, identifying suspicious behavior, child detection.
  • Traffic monitoring: identifying traffic jams, catching drivers that are breaking the speed limit.
  • Security: face detection, identity verification on a smartphone.
  • Robotics: robotic surgery, agriculture, household chores, warehouses, autonomous delivery.
  • Sports: ball tracking in baseball, golf, and football.
  • Agriculture: disease detection in fruits.
  • Food: food identification.

There are a lot of steps in this tutorial. Have fun, be patient, and be persistent. Don’t give up! If something doesn’t work the first time around, try again. You will learn a lot more by fighting through to the end of this project. Stay relentless!

By the end of this tutorial, you will have the rock-solid confidence to detect and recognize objects in real time on your laptop’s GPU (Graphics Processing Unit) using deep learning.

Let’s get started!

Table of Contents

You Will Need

Install TensorFlow CPU

We need to get all the required software set up on our computer. I will be following this really helpful tutorial.

Open an Anaconda command prompt terminal.

1-open-command-promptJPG

Type the command below to create a virtual environment named tensorflow_cpu that has Python 3.6 installed. 

conda create -n tensorflow_cpu pip python=3.6

Press y and then ENTER.

A virtual environment is like an independent Python workspace which has its own set of libraries and Python version installed. For example, you might have a project that needs to run using an older version of Python, like Python 2.7. You might have another project that requires Python 3.7. You can create separate virtual environments for these projects.

Now, let’s activate the virtual environment by using this command:

conda activate tensorflow_cpu
2-activate-virtual-environmetJPG

Type the following command to install TensorFlow CPU.

pip install --ignore-installed --upgrade tensorflow==1.9

Wait for Tensorflow CPU to finish installing. Once it is finished installing, launch Python by typing the following command:

python
3-launch-pythonJPG

Type:

import tensorflow as tf

Here is what my screen looks like now:

4-import-tensorflowJPG

Now type the following:

hello = tf.constant('Hello, TensorFlow!')
sess = tf.Session()

You should see a message that says: “Your CPU supports instructions that this TensorFlow binary….”. Just ignore that. Your TensorFlow will still run fine.

Now run this command to complete the test of the installation:

print(sess.run(hello))
6-test-installationJPG

Press CTRL+Z. Then press ENTER to exit.

Type:

exit

That’s it for TensorFlow CPU. Now let’s install TensorFlow GPU.

Return to Table of Contents

Install TensorFlow GPU

Your system must have the following requirements:

  • Nvidia GPU (GTX 650 or newer…I’ll show you later how to find out what Nvidia GPU version is in your computer)
  • CUDA Toolkit v9.0 (we will install this later in this tutorial)
  • CuDNN v7.0.5 (we will install this later in this tutorial)
  • Anaconda with Python 3.7+

Here is a good tutorial that walks through the installation, but I’ll outline all the steps below.

Install CUDA Toolkit v9.0

The first thing we need to do is to install the CUDA Toolkit v9.0. Go to this link.

Select your operating system. In my case, I will select Windows, x86_64, Version 10, and exe (local).

7-select-target-platformJPG

Download the Base Installer as well as all the patches. I downloaded all these files to my Desktop. It will take a while to download, so just wait while your computer downloads everything.

8-base-installerJPG
9-patchesJPG

Open the folder where the downloads were saved to.

10-downloaded-to-desktopJPG

Double-click on the Base Installer program, the largest of the files that you downloaded from the website.

Click Yes to allow the program to make changes to your device.

Click OK to extract the files to your computer.

11-click-okJPG
12-extract-filesJPG

I saw this error window. Just click Continue.

13-error-message-continueJPG

Click Agree and Continue.

14-agree-and-continueJPG

If you saw that error window earlier… “…you may not be able to run CUDA applications with this driver…,” select the Custom (Advanced) install option and click Next. Otherwise, do the Express installation and follow all the prompts.

15-custom-advancedJPG

Uncheck the Driver components, PhysX, and Visual Studio Integration options. Then click Next.

Click Next.

16-installation-location-click-nextJPG

Wait for everything to install.

17-prepare-for-installationJPG

Click Close.

18-installer-finishedJPG

Delete  C:\Program Files\NVIDIA Corporation\Installer2.

19-delete-installer-2JPG

Double-click on Patch 1.

Click Yes to allow changes to your computer.

Click OK.

20-click-okJPG

Click Agree and Continue.

21-agree-and-continueJPG

Go to Custom (Advanced) and click Next.

22-custom-advancedJPG

Click Next.

23-click-nextJPG

Click Close.

The process is the same for Patch 2. Double-click on Patch 2 now.

Click Yes to allow changes to your computer.

Click OK.

Click Agree and Continue.

Go to Custom (Advanced) and click Next.

Click Next.

24-click-nextJPG

Click Close.

25-click-closeJPG

The process is the same for Patch 3. Double-click on Patch 3 now.

Click Yes to allow changes to your computer.

Click OK.

Click Agree and Continue.

Go to Custom (Advanced) and click Next.

Click Next.

Click Close.

The process is the same for Patch 4. Double-click on Patch 4 now.

Click Yes to allow changes to your computer.

Click OK.

Click Agree and Continue.

Go to Custom (Advanced) and click Next.

Click Next.

After you’ve installed Patch 4, your screen should look like this:

26-installed-patch-4JPG

Click Close.

To verify your CUDA installation, go to the command terminal on your computer, and type:

nvcc --version
26-verify-cuda-versionJPG

Return to Table of Contents

Install the NVIDIA CUDA Deep Neural Network library (cuDNN)

Now that we installed the CUDA 9.0 base installer and its four patches, we need to install the NVIDIA CUDA Deep Neural Network library (cuDNN). Official instructions for installing are on this page, but I’ll walk you through the process below.

Go to https://developer.nvidia.com/rdp/cudnn-download

Create a user profile if needed and log in.

27-become-a-memberJPG

Go to this page: https://developer.nvidia.com/rdp/cudnn-download

Agree to the terms of the cuDNN Software License Agreement.

28-agree-to-termsJPG

We have CUDA 9.0, so we need to click cuDNN v7.6.4 (September 27, 2019), for CUDA 9.0.

29-download-cudnnJPG

I have Windows 10, so I will download cuDNN Library for Windows 10.

30-cudnn-windows10JPG

In my case, the zip file downloaded to my Desktop. I will unzip that zip file now, which will create a new folder of the same name…just without the .zip part. These are your cuDNN files. We’ll come back to these in a second.

31-unzipJPG

Before we get going, let’s double check what GPU we have. If you are on a Windows machine, search for the “Device Manager.”

32-my-gpuJPG

Once you have the Device Manager open, you should see an option near the top for “Display Adapters.” Click the drop-down arrow next to that, and you should see the name of your GPU. Mine is NVIDIA GeForce GTX 1060.

33-nvidia-control-panelJPG

If you are on Windows, you can also check what NVIDIA graphics driver you have by right-clicking on your Desktop and clicking the NVIDIA Control Panel. My version is 430.86. This version fits the requirements for cuDNN.

Ok, now that we have verified that our system meets the requirements, lets navigate to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0, your CUDA Toolkit directory.

34-navigate-to-cuda-toolkit-directoryJPG

Now go to your cuDNN files, that new folder that was created when you did the unzipping. Inside that folder, you should see a folder named cuda. Click on it.

35-named-cudaJPG

Click bin.

36-click-binJPG

Copy cudnn64_7.dll to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\bin. Your computer might ask you to allow Administrative Privileges. Just click Continue when you see that prompt.

Now go back to your cuDNN files. Inside the cuda folder, click on include. You should see a file named cudnn.h.

37-click-includeJPG
38-cudnnhJPG

Copy that file to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\include. Your computer might ask you to allow Administrative Privileges. Just click Continue when you see that prompt.

Now go back to your cuDNN files. Inside the cuda folder, click on lib -> x64. You should see a file named cudnn.lib. 

39-cudnn-libJPG

Copy that file to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\lib\x64. Your computer might ask you to allow Administrative Privileges. Just click Continue when you see that prompt.

If you are using Windows, do a search on your computer for Environment Variables. An option should pop up to allow you to edit the Environment Variables on your computer.

Click on Environment Variables.

40-environment-variablesJPG

Make sure you CUDA_PATH variable is set to C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0.

41-cuda-path-setJPG

I recommend restarting your computer now.

Return to Table of Contents

Install TensorFlow GPU

Now we need to install TensorFlow GPU. Open a new Anaconda terminal window. 

42-anaconda-terminal-windowJPG

Create a new Conda virtual environment named tensorflow_gpu by typing this command:

conda create -n tensorflow_gpu pip python=3.6

Type y and press Enter.

43-conda-virtual-environmentJPG

Activate the virtual environment.

conda activate tensorflow_gpu
44-activate-virtual-envJPG

Install TensorFlow GPU for Python.

pip install --ignore-installed --upgrade tensorflow-gpu==1.9

Wait for TensorFlow GPU to install.

Now let’s test the installation. Launch the Python interpreter.

python

Type this command.

import tensorflow as tf

If you don’t see an error, TensorFlow GPU is successfully installed.

45-test-installation-1JPG

Now type this:

hello = tf.constant('Hello, TensorFlow!')
46-now-type-thisJPG

And run this command. It might take a few minutes to run, so just wait until it finishes:

sess = tf.Session()
47-all-finishedJPG

Now type this command to complete the test of the installation:

print(sess.run(hello))
48-complete-the-testJPG

You can further confirm whether TensorFlow can access the GPU, by typing the following into the Python interpreter (just copy and paste into the terminal window while the Python interpreter is running).

tf.test.is_gpu_available(
    cuda_only=True,
    min_cuda_compute_capability=None
)
49-further-testJPG

To exit the Python interpreter, type:

exit()
50-exit-the-editorJPG

And press Enter.

Return to Table of Contents

Install TensorFlow Models

Now that we have everything setup, let’s install some useful libraries. I will show you the steps for doing this in my TensorFlow GPU virtual environment, but the steps are the same for the TensorFlow CPU virtual environment.

Open a new Anaconda terminal window. Let’s take a look at the list of virtual environments that we can activate.

conda env list
51-conda-env-listJPG

I’m going to activate the TensorFlow GPU virtual environment.

conda activate tensorflow_gpu

Install the libraries. Type this command:

conda install pillow lxml jupyter matplotlib opencv cython

Press y to proceed.

Once that is finished, you need to create a folder somewhere that has the TensorFlow Models  (e.g. C:\Users\addis\Documents\TensorFlow). If you have a D drive, you can also save it there as well.

In your Anaconda terminal window, move to the TensorFlow directory you just created. You will use the cd command to change to that directory. For example:

cd C:\Users\addis\Documents\TensorFlow

Go to the TensorFlow models page on GitHub: https://github.com/tensorflow/models.

Click the button to download the zip file of the repository. It is a large file, so it will take a while to download.

52-download-zipJPG

Move the zip folder to the TensorFlow directory you created earlier and extract the contents.

Rename the extracted folder to models instead of models-master. Your TensorFlow directory hierarchy should look like this:

TensorFlow

  • models
    • official
    • research
    • samples
    • tutorials

Return to Table of Contents

Install Protobuf

Now we need to install Protobuf, which is used by the TensorFlow Object Detection API to configure the training and model parameters.

Go to this page: https://github.com/protocolbuffers/protobuf/releases

Download the latest *-win32.zip release (assuming you are on a Windows machine).

53-download-latestJPG

Create a folder in C:\Program Files named it Google Protobuf.

Extract the contents of the downloaded *-win32.zip, inside C:\Program Files\Google Protobuf

54-extract-contentsJPG

Search for Environment Variables on your system. A window should pop up that says System Properties.

55-system-propertiesJPG

Click Environment Variables.

Go down to the Path variable and click Edit.

56-path-variable-editJPG

Click New.

57-click-newJPG

Add C:\Program Files\Google Protobuf\bin

You can also add it the Path System variable.

Click OK a few times to close out all the windows.

Open a new Anaconda terminal window.

I’m going to activate the TensorFlow GPU virtual environment.

conda activate tensorflow_gpu

cd into your \TensorFlow\models\research\ directory and run the following command:

for /f %i in ('dir /b object_detection\protos\*.proto') do protoc object_detection\protos\%i --python_out=.

Now go back to the Environment Variables on your system. Create a New Environment Variable named PYTHONPATH (if you don’t have one already). Replace C:\Python27amd64 if you don’t have Python installed there. Also, replace <your_path> with the path to your TensorFlow folder.

C:\Python27amd64;C:\<your_path>\TensorFlow\models\research\object_detection
58-pythonpathJPG

For example:

C:\Python27amd64;C:\Users\addis\Documents\TensorFlow

Now add these two paths to your PYTHONPATH environment variable:

C:\<your_path>\TensorFlow\models\research\
C:\<your_path>\TensorFlow\models\research\slim

Return to Table of Contents

Install COCO API

Now, we are going to install the COCO API. You don’t need to worry about what this is at this stage. I’ll explain it later.

Download the Visual Studios Build Tools here: Visual C++ 2015 build tools from here: https://go.microsoft.com/fwlink/?LinkId=691126

Choose the default installation.

59-visual-studioJPG

After it has installed, restart your computer.

60-setup-completedJPG

Open a new Anaconda terminal window.

I’m going to activate the TensorFlow GPU virtual environment.

conda activate tensorflow_gpu

cd into your \TensorFlow\models\research\ directory and run the following command to install pycocotools (everything below goes on one line):

pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI
61-pycocotools-installedJPG

If it doesn’t work, install git: https://git-scm.com/download/win

Follow all the default settings for installing Git. You will have to click Next several times.

Once you have finished installing Git, run this command (everything goes on one line):

pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

Return to Table of Contents

Test the Installation

Open a new Anaconda terminal window.

I’m going to activate the TensorFlow GPU virtual environment.

conda activate tensorflow_gpu

cd into your \TensorFlow\models\research\object_detection\builders directory and run the following command to test your installation.

python model_builder_test.py

You should see an OK message.

62-test-your-installationJPG

Return to Table of Contents

Install LabelImg

Now we will install LabelImg, a graphical image annotation tool for labeling object bounding boxes in images.

Open a new Anaconda/Command Prompt window.

Create a new virtual environment named labelImg by typing the following command:

conda create -n labelImg

Activate the virtual environment.

conda activate labelImg

Install pyqt.

conda install pyqt=5

Click y to proceed.

Go to your TensorFlow folder, and create a new folder named addons.

63-new-folder-named-addonsJPG

Change to that directory using the cd command.

Type the following command to clone the repository:

git clone https://github.com/tzutalin/labelImg.git

Wait while labelImg downloads.

You should now have a folder named addons\labelImg under your TensorFlow folder.

Type exit to exit the terminal.

Open a new terminal window.

Activate the TensorFlow GPU virtual environment.

conda activate tensorflow_gpu

cd into your TensorFlow\addons\labelImg directory.

Type the following commands, one right after the other.

conda install pyqt=5
conda install lxml
pyrcc5 -o libs/resources.py resources.qrc
exit

Test the LabelImg Installation

Open a new terminal window.

Activate the TensorFlow GPU virtual environment.

conda activate tensorflow_gpu

cd into your TensorFlow\addons\labelImg directory.

Type the following commands:

python labelImg.py

If you see this window, you have successfully installed LabelImg. Here is a tutorial on how to label your own images. Congratulations!

64-label-imgJPG

Return to Table of Contents

Recognize Objects Using Your WebCam

Approach

Note: This section gets really technical. If you know the basics of computer vision and deep learning, it will make sense. Otherwise, it will not. You can skip this section and head straight to the Implementation section if you are not interested in what is going on under the hood of the object recognition application we are developing.

In this project, we use OpenCV and TensorFlow to create a system capable of automatically recognizing objects in a webcam. Each detected object is outlined with a bounding box labeled with the predicted object type as well as a detection score.

The detection score is the probability that a bounding box contains the object of a particular type (e.g. the confidence a model has that an object identified as a “backpack” is actually a backpack).

The particular SSD with Inception v2 model used in this project is the ssd_inception_v2_coco model. The ssd_inception_v2_coco model uses the Single Shot MultiBox Detector (SSD) for its architecture and the Inception v2 framework for feature extraction.

Single Shot MultiBox Detector (SSD)

Most state-of-the-art object detection methods involve the following stages:

  1. Hypothesize bounding boxes 
  2. Resample pixels or features for each box
  3. Apply a classifier

The Single Shot MultiBox Detector (SSD) eliminates the multi-stage process above and performs all object detection computations using just a single deep neural network.

Inception v2

Most state-of-the-art object detection methods based on convolutional neural networks at the time of the invention of Inception v2 added increasingly more convolution layers or neurons per layer in order to achieve greater accuracy. The problem with this approach is that it is computationally expensive and prone to overfitting. The Inception v2 architecture (as well as the Inception v3 architecture) was proposed in order to address these shortcomings.

Rather than stacking multiple kernel filter sizes sequentially within a convolutional neural network, the approach of the inception-based model is to perform a convolution on an input with multiple kernels all operating at the same layer of the network. By factorizing convolutions and using aggressive regularization, the authors were able to improve computational efficiency. Inception v2 factorizes the traditional 7 x 7 convolution into 3 x 3 convolutions.

Szegedy, Vanhoucke, Ioffe, Shlens, & Wojna, (2015) conducted an empirically-based demonstration in their landmark Inception v2 paper, which showed that factorizing convolutions and using aggressive dimensionality reduction can substantially lower computational cost while maintaining accuracy.

Data Set

The ssd_inception_v2_coco model used in this project is pretrained on the Common Objects in Context (COCO) data set (COCO data set), a large-scale data set that contains 1.5 million object instances and more than 200,000 labeled images. The COCO data required 70,000 crowd worker hours to gather, annotate, and organize images of objects in natural environments.

Software Dependencies

The following libraries form the object recognition backbone of the application implemented in this project:

  • OpenCV, a library of programming functions for computer vision.
  • Pillow, a library for manipulating images.
  • Numpy, a library for scientific computing.
  • Matplotlib, a library for creating graphs and visualizations.
  • TensorFlow Object Detection API, an open source framework developed by Google that enables the development, training, and deployment of pre-trained object detection models.

Return to Table of Contents

Implementation

Now to the fun part, we will now recognize objects using our computer webcam.

Copy the following program, and save it to your TensorFlow\models\research\object_detection directory as object_detection_test.py .

# Import all the key libraries
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import cv2

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
from utils import label_map_util
from utils import visualization_utils as vis_util

# Define the video stream
cap = cv2.VideoCapture(0)  

# Which model are we downloading?
# The models are listed here: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md
MODEL_NAME = 'ssd_inception_v2_coco_2018_01_28'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to the frozen detection graph. 
# This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add the correct label for each box.
PATH_TO_LABELS = os.path.join('data', 'mscoco_label_map.pbtxt')

# Number of classes to detect
NUM_CLASSES = 90

# Download Model
opener = urllib.request.URLopener()
opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
tar_file = tarfile.open(MODEL_FILE)
for file in tar_file.getmembers():
    file_name = os.path.basename(file.name)
    if 'frozen_inference_graph.pb' in file_name:
        tar_file.extract(file, os.getcwd())

# Load a (frozen) Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

# Loading label map
# Label maps map indices to category names, so that when our convolution network 
# predicts `5`, we know that this corresponds to `airplane`.  Here we use internal 
# utility functions, but anything that returns a dictionary mapping integers to 
# appropriate string labels would be fine
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(
    label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)


# Helper code
def load_image_into_numpy_array(image):
    (im_width, im_height) = image.size
    return np.array(image.getdata()).reshape(
        (im_height, im_width, 3)).astype(np.uint8)
	
# Detection
with detection_graph.as_default():
    with tf.Session(graph=detection_graph) as sess:
        while True:

            # Read frame from camera
            ret, image_np = cap.read()
            # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
            image_np_expanded = np.expand_dims(image_np, axis=0)
            # Extract image tensor
            image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
            # Extract detection boxes
            boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
            # Extract detection scores
            scores = detection_graph.get_tensor_by_name('detection_scores:0')
            # Extract detection classes
            classes = detection_graph.get_tensor_by_name('detection_classes:0')
            # Extract number of detectionsd
            num_detections = detection_graph.get_tensor_by_name(
                'num_detections:0')
            # Actual detection.
            (boxes, scores, classes, num_detections) = sess.run(
                [boxes, scores, classes, num_detections],
                feed_dict={image_tensor: image_np_expanded})
            # Visualization of the results of a detection.
            vis_util.visualize_boxes_and_labels_on_image_array(
                image_np,
                np.squeeze(boxes),
                np.squeeze(classes).astype(np.int32),
                np.squeeze(scores),
                category_index,
                use_normalized_coordinates=True,
                line_thickness=8)

            # Display output
            cv2.imshow('object detection', cv2.resize(image_np, (800, 600)))

            if cv2.waitKey(25) & 0xFF == ord('q'):
                cv2.destroyAllWindows()
                break


print("We are finished! That was fun!")

Open a new terminal window.

Activate the TensorFlow GPU virtual environment.

conda activate tensorflow_gpu

cd into your TensorFlow\models\research\object_detection directory.

At the time of this writing, we need to use Numpy version 1.16.4. Type the following command to see what version of Numpy you have on your system.

pip show numpy

If it is not 1.16.4, execute the following commands:

pip uninstall numpy
pip install numpy==1.16.4

Now run, your program:

python object_detection_test.py

In about 30 to 90 seconds, you should see your webcam power up and object recognition take action. That’s it! Congratulations for making it to the end of this tutorial!

object_detection_resultsJPG

Keep building!

Return to Table of Contents