How Do Neural Networks Make Predictions?

Neural networks are the workhorses of the rapidly growing field known as deep learning. Neural networks are used for all sorts of applications where a prediction of some sort is desired. Here are some examples:

  • Predicting the type of objects in an image or video
  • Sales forecasting
  • Speech recognition
  • Medical diagnosis
  • Risk management
  • and countless other applications… 

In this post, I will explain how neural networks make those predictions by boiling these structures down to their fundamental parts and then building up from there.

You Will Need 

Create Your First Neural Network

Imagine you run a business that provides short online courses for working professionals. Some of your courses are free, but your best courses require the students to pay for a subscription. 

You want to create a neural network to predict if a free student is likely to upgrade to a paid subscription. Let’s create the most basic neural network you can make.

1-first-neural-networkJPG

OK, so there is our neural network. To implement this neural network on a computer, we need to translate this diagram into a software program. Let’s do that now using Python, the most popular language for machine learning.

# Declare a variable named weight and 
# initiate it with a value
weight = 0.075

# Create a method called neural_network that 
# takes as inputs, the input data (number of 
free courses a student has taken during the 
# last 30 days) and the weight of the connection. 
# The method returns the prediction.

def neural_network(input, weight):

  # The input data multiplied by the weight 
  # equals the prediction
  prediction = input * weight

  # This is the output
  return prediction

So we currently have five students, all of whom are free students. The number of free courses these users have taken during the last 30 days is 12, 3, 5, 6, and 8. Let’s code this in Python as a list.

number_of_free_courses_taken = [12, 3, 5, 6, 8]

Let’s make a prediction for the first student, the one who has taken 12 free courses over the last 30 days.

2-first-neural-networkJPG

Now let’s put the diagram into code.

# Extract the first value of the list...12...
# and store into a variable named input
first_student_input = number_of_free_courses_taken[0]

# Call the neural_network method and store the 
# prediction result into a variable
first_student_prediction = neural_network(
                         first_student_input, weight)

# Print the prediction
print(first_student_prediction)

OK. We have finished the code. Let’s see how it looks all together.

weight = 0.075

def neural_network(input, weight):

  prediction = input * weight

  return prediction

number_of_free_courses_taken = [
                        12, 3, 5, 6, 8]

first_student_input = number_of_free_courses_taken[0]

first_student_prediction = neural_network(
                       first_student_input, weight)

print(first_student_prediction)

Open a Jupyter Notebook and run the code above, or run the code inside your favorite Python IDE.

Here is what I got:

run-code

What did you get? Did you get 0.9? If so, congratulations!

Let’s see what is happening when we run our code. We called the neural_network method. The first operation performed inside that method is to multiply the input by the weight and return the result. In this case, the input is 12, and the weight is 0.075. The result is 0.9.

3-making-predictionsJPG

0.9 is stored in the first_student_prediction variable.

4-making-predictionJPG

And this, my friend, is the most basic building block of a neural network. A neural network in its simplest form consists of one or more weights which you can multiply by input data to make a prediction

Let’s take a look at some questions you might have at this stage.

What kind of input data can go into a neural network?

Real numbers that can be measured or calculated somewhere in the real world. Yesterday’s high temperature, a medical patient’s blood pressure reading, previous year’s rainfall, or average annual rainfall are all valid inputs into a neural network. Negative numbers are totally acceptable as well.

A good rule of thumb is, if you can quantify it, you can use it as an input into a neural network. It is best to use input data into a neural network that you think will be relevant for making the prediction you desire.

For example, if you are trying to create a neural network to predict if a patient has breast cancer or not, how many fingers a person has probably not going to be all that relevant. However, how many days per month a patient exercises is likely to be a relevant piece of input data that you would want to feed into your neural network.

What does a neural network predict?

A neural network outputs some real number. In some neural network implementations, we can do some fancy mathematics to limit the output to some real number between 0 and 1. Why would we want to do that? Well in some applications we might want to output probabilities. Let me explain.

Suppose you want to predict the probability that tomorrow will be sunny. The input into a neural network to make such a prediction could be today’s high temperature. 

5-high-temperatureJPG

If the output is some number like 0.30, we can interpret this as a 30% change of the weather being sunny tomorrow given today’s high temperature. Pretty cool huh!

We don’t have to limit the output to between 0 and 1. For example, let’s say we have a neural network designed to predict the price of a house given the house’s area in square feet. Such a network might tell us, “given the house’s area in square feet, the predicted price of the house is $432,000.”

What happens if the neural network’s predictions are incorrect?

The neural network will adjust its weights so that the next time it makes a more accurate prediction. Recall that the weights are multiplied by the input values to make a prediction.

What is a neural network really learning?

A neural network is learning the best possible set of weights. “Best” in the context of neural networks means the weights that minimize the prediction error.

Remember, the core math operation in a neural network is multiplication, where the simplest neural network is:

Input Value * Weight = Prediction

How does the neural network find the best set of weights?

Short answer: Trial and error

Long answer: A neural network starts out with random numbers for weights. It then takes in a single input data point, makes a prediction, and then sees if its prediction was either too high or too low. The neural network then adjusts its weight(s) accordingly so that the next time it sees the same input data point, it makes a more accurate prediction.

Once the weights are adjusted, the neural network is fed the next data point, and so on. A neural network gets better and better each time it makes a prediction. It “learns” from its mistakes one data point at a time.

Do you notice something here?

Standard neural networks have no memory. They are fed an input data point, make a prediction, see how close the prediction was to reality, adjust the weights accordingly, and then move on to the next data point. At each step of the learning process of a neural network, it has no memory of the most recent prediction it made.

Standard neural networks focus on one input data point at a time. For example, in our subscriber prediction neural network we built earlier in this tutorial, if we feed our neural network number_of_free_courses_taken[1], it will have no clue what it predicted when number_of_free_courses_taken[0] was the input value.

There are some networks that have short term memories. These are called Long short-term memory networks (LSTM).

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

How to Install TensorFlow 2 on Windows 10

In this post, I will show you how to install TensorFlow 2 on Windows 10. TensorFlow2 is a free software library used for machine learning applications. It comes integrated with Keras, a neural-network library written in Python. If you want to work with neural networks and deep learning, TensorFlow 2 should be your software of choice because of its popularity both in academia and in industry. Let’s get started!

Table of Contents

You Will Need 

Directions

Install TensorFlow 2

Here are the official instructions for downloading TensorFlow 2, but I will walk you through the process step-by-step.

Open an Anaconda command prompt terminal.

1-open-promptJPG

Type the command below to create a virtual environment named tf_2 with the latest version of Python installed. 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.

conda create -n tf_2 python

Press y and then ENTER.

2-type-yJPG

Wait for the software to download.

3-activate-tensorflow-2JPG

Once the download is finished, activate the virtual environment using this command:

conda activate tf_2

Check which version of Python you have installed on your system. I have Python 3.8.0.

python --version
4-python-versionJPG

Choose a TensorFlow package. I’ll install TensorFlow CPU. Let’s type the following command:

5-choose-a-packageJPG
pip install --upgrade tensorflow

You might see this error:

ERROR: Could not find a version that satisfies the requirement tensorflow (from versions: none)

ERROR: No matching distribution found for tensorflow

If you do, you need to downgrade your version of Python. TensorFlow is not yet compatible with your newest version of Python.

conda install python=3.6

Press y and then ENTER.

Check which version of Python you have installed on your system. I have Python 3.6.9 now.

python --version
6-downgrade-pythonJPG

Now install TensorFlow 2.

pip install --upgrade tensorflow

Wait for Tensorflow CPU to finish installing. Once it is finished installing, verify the installation by typing:

python -c "import tensorflow as tf; x = [[2.]]; print('tensorflow version', tf.__version__); print('hello, {}'.format(tf.matmul(x, x)))"

Here is the output:

9-voilaJPG

You should see your TensorFlow version in the output.

You might see this message:

“I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2”

Don’t worry, TensorFlow is working just fine. To get rid of that message, you can set the environment variables inside the virtual environment. Type the following command:

set TF_CPP_MIN_LOG_LEVEL=2

Now run this command:

python -c "import tensorflow as tf; x = [[2.]]; print('tensorflow version', tf.__version__); print('hello, {}'.format(tf.matmul(x, x)))"

Voila! Message gone. 

9-voilaJPG-1

Return to Table of Contents

Create a Basic Neural Network Using TensorFlow 2

To really see what TensorFlow 2 can do, let’s do the following:

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

We are going to roughly follow the TensorFlow beginner tutorial.

First, install the Matplotlib library.

pip install matplotlib

I’m now going to open up a text editor and type a Python program. I will save it to my D drive as fashion_mnist.py. Here is the code:

from __future__ import absolute_import, division, print_function, unicode_literals

# Import the key libraries
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np

# Rename tf.keras.layers
layers = tf.keras.layers

# Print the TensorFlow version
print(tf.__version__)

# Load and prepare the MNIST dataset. 
# Convert the samples from integers to floating-point numbers:
mnist = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

# Let's plot the data so we can see it
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal',
 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
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(x_train[i], cmap=plt.cm.binary)
 plt.xlabel(class_names[y_train[i]])
plt.show()

Within your virtual environment in the Anaconda terminal, navigate to where you saved your code. I will type.

D:

Then:

cd D:\<YOUR_PATH>\install_tensorflow2

Type dir to see if the Python (.py) file is in that directory.

Now run the code:

python fashion_mnist.py

You should see this graphic pop up.

10-fashion-datasetJPG

In the terminal window, press CTRL+C on your keyboard to stop the code from running.

Let’s add to our code. Open up the Python file again in the text editor and type the following code. If you are new to neural networks, don’t worry what everything means at this stage.

from __future__ import absolute_import, division, print_function, unicode_literals

# Import the key libraries
import matplotlib.pyplot as plt
import tensorflow as tf
import numpy as np

# Rename tf.keras.layers
layers = tf.keras.layers

# Print the TensorFlow version
print(tf.__version__)

# Load and prepare the MNIST dataset. 
# Convert the samples from integers to floating-point numbers:
mnist = tf.keras.datasets.fashion_mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

# Let's plot the data so we can see it
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal',
 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
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(x_train[i], cmap=plt.cm.binary)
 plt.xlabel(class_names[y_train[i]])
plt.show()

# Build the neural network layer-by-layer
model = tf.keras.Sequential()
model.add(layers.Flatten()) # Make the input layer one-dimensional
model.add(layers.Dense(64, activation='relu')) # Layer has 64 nodes; Uses ReLU
model.add(layers.Dense(64, activation='relu')) # Layer has 64 nodes; Uses ReLU
model.add(layers.Dense(10, activation='softmax')) # Layer has 64 nodes; Uses Softmax

# Choose an optimizer and loss function for training:
model.compile(optimizer='adam',
 loss='sparse_categorical_crossentropy',
 metrics=['accuracy'])
 
# Train and evaluate the model's accuracy
model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test,  y_test, verbose=2)

Run the code:

python fashion_mnist.py

When you see the plot of the clothes appear, just close that window so that the neural network build and run.

Here is the output.

11-accuracyJPG

The accuracy of classifying the clothing items was 87.5%. Pretty cool huh! Congratulations! You’ve built and run your first neural network on TensorFlow 2.

To deactivate the virtual environment, type:

conda deactivate

Then to exit the terminal, type:

exit

At this stage, I encourage you to go through the TensorFlow tutorials to get more practice using this really powerful tool.

Return to Table of Contents