In general, there are two ways to install Keras and TensorFlow:

Install a Python distribution that includes hundreds of popular packages (including Keras and TensorFlow) such as ActivePython. Use pip to install TensorFlow, which will also install Keras at the same time.

we use pip to install

TensorFlow Requirements

TensorFlow and Keras require Python 3.6+ (Python 3.8 requires TensorFlow 2.2+) , and the latest version of pip. You can determine the version of Python installed on your computer by running the following command:

    python3 --version

Output should be similar to:

    Python 3.8.2

Run the following command to ensure that the latest version of pip is installed:

pip install --upgrade pip

To install TensorFlow for CPU and GPU processors, run the following command:

pip install tensorflow

The installation installs a slew of TensorFlow and Keras dependencies:

tensorflow                                 
├── absl-py~=0.10                          
│   └── six                                
├── astunparse~=1.6.3                      
│   ├── six<2.0,>=1.6.1                    
│   └── wheel<1.0,>=0.23.0                 
├── flatbuffers~=1.12.0                    
├── gast==0.3.3                            
├── google-pasta~=0.2                      
│   └── six                                
├── grpcio~=1.32.0                         
│   └── six>=1.5.2                         
├── h5py~=2.10.0                           
│   ├── numpy>=1.7                         
│   └── six                                
├── keras-preprocessing~=1.1.2             
│   ├── numpy>=1.9.1                       
│   └── six>=1.9.0                         
├── numpy~=1.19.2                          
├── opt-einsum~=3.3.0                      
│   └── numpy>=1.7                         
├── protobuf>=3.9.2                        
│   └── six>=1.9                           
├── six~=1.15.0                            
├── tensorboard~=2.4                       
│   ├── absl-py>=0.4                       
│   │   └── six                            
│   ├── google-auth-oauthlib<0.5,>=0.4.1   
│   │   ├── google-auth>=1.0.0             
│   │   │   ├── cachetools<5.0,>=2.0.0     
│   │   │   ├── pyasn1-modules>=0.2.1      
│   │   │   │   └── pyasn1<0.5.0,>=0.4.6   
│   │   │   ├── rsa<5,>=3.1.4              
│   │   │   │   └── pyasn1>=0.1.3          
│   │   │   ├── setuptools>=40.3.0         
│   │   │   └── six>=1.9.0                 
│   │   └── requests-oauthlib>=0.7.0       
│   │       ├── oauthlib>=3.0.0            
│   │       └── requests>=2.0.0            
│   │           ├── certifi>=2017.4.17     
│   │           ├── chardet<5,>=3.0.2      
│   │           ├── idna<3,>=2.5           
│   │           └── urllib3<1.27,>=1.21.1  
│   ├── google-auth<2,>=1.6.3              
│   │   ├── cachetools<5.0,>=2.0.0         
│   │   ├── pyasn1-modules>=0.2.1          
│   │   │   └── pyasn1<0.5.0,>=0.4.6       
│   │   ├── rsa<5,>=3.1.4                  
│   │   │   └── pyasn1>=0.1.3              
│   │   ├── setuptools>=40.3.0             
│   │   └── six>=1.9.0                     
│   ├── grpcio>=1.24.3                     
│   │   └── six>=1.5.2                     
│   ├── markdown>=2.6.8                    
│   ├── numpy>=1.12.0                      
│   ├── protobuf>=3.6.0                    
│   │   └── six>=1.9                       
│   ├── requests<3,>=2.21.0                
│   │   ├── certifi>=2017.4.17             
│   │   ├── chardet<5,>=3.0.2              
│   │   ├── idna<3,>=2.5                   
│   │   └── urllib3<1.27,>=1.21.1          
│   ├── setuptools>=41.0.0                 
│   ├── six>=1.10.0                        
│   ├── tensorboard-plugin-wit>=1.6.0      
│   ├── werkzeug>=0.11.15                  
│   └── wheel>=0.26                        
├── tensorflow-estimator<2.5.0,>=2.4.0    
├── termcolor~=1.1.0                       
├── typing-extensions~=3.7.4               
├── wheel~=0.35                            
└── wrapt~=1.12.1

In the diagram above we can see that Numpy and Keras are installed among the dependencies.

But we must install other dependencies such as seaborn

Seaborn is a Python data visualization library based on matplotlib. It provides a high-level interface for drawing attractive and informative statistical .

pip install seaborn

4. Now we only have to download our data set and the project you can download it from (https://disk.yandex.com/d/1hi6kB_WQUp42g "is a compressed .rar file, that is the complete structure of our project.")

5. We must unzip our project on the desktop of our pc in a folder according to the following folder structure

├── Vehicle_Recognition_Project
│   ├── .ipynb_checkpoints
│   ├── Prediction
│   ├── test_set
│   │   ├── cars              
│   │   ├── Emergency_Vehicles
│   │   └── suv
│   ├── training_set
│   │   ├── cars
│   │   ├── Emergency_Vehicles
│   │   └── suv
│   └── Vehicle_Recognition.ipynb

Executing our Project

1. First we must run Jupyter Notebook (Anaconda3) and it will display a portal like the following in which we must click on the file Vehicle_Recognition.ipynb this opens a second window in the browser that displays our code on a line.

2. We are going to restart by clicking on the Kernel menu and select the option from the drop down menu "Subtract & Clear Ouput " as shown in the following image.

this allows us to restart our kernel to be able to run our image recognition code from scratch.

we must confirm

3. Now we are ready to start running our code, to start we must click on the first line of code and then hit the RUN button in the Jupyter Notebook client-server menu.

4. Line by line we are executing the Run button and this will execute each line of code and will show its respective processing in the Local Server.