Scribd
Upload
27 views10 pages

1 Keras

Uploaded by

simhadribaby207
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
27 views10 pages

1 Keras

Uploaded by

simhadribaby207
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Deployment: Keras models can be easily deployed in production en

vironments, including integration with TensorFlow Serving for scala


ble deployment.

Distributed Training: Keras supports distributed training, enabling


you to train models on multiple GPUs or across different machines.

Deep Learning Research: It is extensively used in deep learning


research and competitions due to its flexibility and ease of use.

Hyperparameter Tuning: It supports hyperparameter tuning, allow


ing you to optimize your models for better accuracy.

Keras is designed to be modular and extensible, making it a


great choice for both beginners and experienced practitioner
s in the field of machine learning
Keras is a powerful and userfriendly library for
deep learning, and it's widely used in various machine
learning applications.
Here are some common uses of Keras in machine learning:
Building Neural Networks: Keras provides high-
level building blocks for developing deep learning models,
making it easy to create and train neural networks.

Data Preprocessing: It offers tools for data preprocessing,


such as data augmentation and normalization, which are
essential for improving model performance.

Model Evaluation: Keras includes functionalities for


evaluating model performance, including metrics and loss
functions
INSTALLATION OF KERAS:
Let us go through the basic requirements of keras
→ Any kind of OS (windows, linux a MAC)
→ Python version 3.5 (or) higher
Python:
→keras is python based neural network library
→Firstly, Python must be installed on your machine
→If the python is properly installed on your machine then open your terminal & type python
python 3.65(V3.65;f09c093264, 10 April 2023, 10:00:01[MSCV. 1900 64 bit (AMD64)) en win32
Type "help" "copyright", "credit “(or) for more information>>>
→If the python is not properly installed on your machine then visit the official python link wwwpython & download the
latest version on your Machine.
KERAS Installation steps:
Step-1:-Create virtual environment
virtual environment is used to manage python packages for different Projects. it also he helps to avoid the breaking the
packages installed in other & environment, so it is always recommended to use Virtual environment while developing
python application
Linux/MAC OS-Linux or MAC OS user go to your project root directory & type like below command to create the virtual
environment
*Python 3-m venu keras Env
After exceuting this command keras env directory is created with bin lib & include folders in your installation location
Windows-In windows OS users use the below command to create the Virtual Environment
py.m Venv Keras
Step2: Activate the environment
In this step it will configure python & pip executables in your shell part
Linux/Mac os: we have created a Virtual environment "Keras venu we type the below command to accurate the Enviroment
$ cd kerasvenv $ Sourcebin/activate
Windows: Windows users move into kerasenv folder & type the below command
/en/script/activate
Step 3: python libraries
Keras depends on following python libraries
-Numpy -Matplotlib
-pandas -Scipy
-scikit-learn -Seaborn
we have installed all the above libraries on our system, these libraries are not installed,
then we use below commands one by one:
Numpy-pip install Numpy --- collecting Numpy downloading...
Pandas-pip install pandas --- collecting pandas downloading...
Matplotlib-pip install Matplotlib ---collecting matplotlib downloading...
Scipy-pip install scipy --- collecting scipy downloading
Scikit-learn-It is an open Source Ml library. it is used for classification, regression & clustering algorithms before installation it requries the following:
Python 3.5(01) higher
Numpy version 1.11.0(or) higher
Scipy version 0.11(or)higher
Now we install scikit.learn library: pipinstall-Scikit.learn
Seaborn-Seaborn is an amazing library that allows for easy visualization of data we use following command to install Seaborn
collecting Seaborn downloading….After, final installation of Keras we get the following response
(Sucessfully installed cycler -0.10.0 Kiwisolver-1.1.0 matplotlib 3.1.1 pandas 0.25.0 py parsing 2.4.2 Python.data vfile 2.8.0 pyt
3-2019.2 Seaborn 0.9.0)

You might also like