Free Udemy Courses

CNN for Computer Vision with Keras and TensorFlow in Python

PUBLISHER :- Start-Tech Academy

LANGUAGE :- English

PRIZE :- 117.38$ 0$

CNN for Computer Vision with Keras and TensorFlow in Python


  • People pursuing a career in data science
  • Working Professionals beginning their Deep Learning journey
  • Anyone curious to master image recognition from Beginner level in short span of time


  • Students will need to install Python and Anaconda software but we have a separate lecture to help you install the sameStudents will need to install Python and Anaconda software but we have a separate lecture to help you install the same


  • Get a strong comprehension of Convolutional Neural Organizations (CNN) and Profound Learning
  • Fabricate a start to finish Picture acknowledgment venture in Python
  • Learn utilization of Keras and Tensorflow libraries
  • Utilize Counterfeit Neural Organizations (ANN) to make forecasts
  • Use Pandas DataFrames to manipulate data and make statistical computations.


You’re searching for a total Convolutional Neural Organization (CNN) course that trains you all that you have to make a Picture Acknowledgment model in Python, correct?

You’ve discovered the privilege Convolutional Neural Organizations course!

In the wake of finishing this course you will have the option to:

  • Recognize the Picture Acknowledgment issues which can be illuminated utilizing CNN Models.
  • Make CNN models in Python utilizing Keras and Tensorflow libraries and break down their outcomes.
  • Unquestionably practice, examine and see Profound Learning ideas
  • Have an away from of Cutting edge Picture Acknowledgment models, for example, LeNet, GoogleNet, VGG16 and so forth.

How this course will support you?

An Evident Declaration of Finishing is introduced to all understudies who embrace this Convolutional Neural organizations course.

In the event that you are an Examiner or a ML researcher, or an understudy who needs to learn and apply Profound learning in True picture acknowledgment issues, this course will give you a strong base for that by showing you probably the most progressive ideas of Profound Learning and their usage in Python without getting excessively Numerical.

For what reason would it be advisable for you to pick this course?

This course covers everything the means that one ought to require to make a picture acknowledgment model utilizing Convolutional Neural Organizations.

Most courses just spotlight on training how to run the investigation yet we accept that having a solid hypothetical comprehension of the ideas empowers us to make a decent model . Furthermore, in the wake of running the investigation, one ought to have the option to decide how great the model is and decipher the outcomes to really have the option to support the business.

What makes us qualified to educate you?

The course is educated by Abhishek and Pukhraj. As directors in Worldwide Examination Counseling firm, we have helped organizations tackle their business issue utilizing Profound learning procedures and we have utilized our experience to remember the reasonable parts of information investigation for this course

We are additionally the makers of the absolute most mainstream online courses – with more than 300,000 enlistments and a great many 5-star surveys like these ones:

This is generally excellent, I love the reality the all clarification given can be perceived by a layman – Joshua

Much obliged to you Creator for this awesome course. You are the best and this course merits any cost. – Daisy

Our Guarantee

Training our understudies is our activity and we are focused on it. In the event that you have any inquiries concerning the course content, practice sheet or anything identified with any subject, you can generally post an inquiry in the course or send us an immediate message.

Download Practice documents, take Practice test, and complete Tasks

With each talk, there are class notes joined for you to track. You can likewise take practice test to check your comprehension of ideas. There is a last down to earth task for you to essentially actualize your learning.

What is canvassed in this course?

This course shows you all the means of making a Neural organization based model for example a Profound Learning model, to tackle business issues.

The following are the course substance of this seminar on ANN:

Section 1 (Segment 2)- Python Basics

This part kicks you off with Python.

This part will assist you with setting up the python and Jupyter condition on your framework and it’ll show you how to play out some fundamental tasks in Python. We will comprehend the significance of various libraries, for example, Numpy, Pandas and Seaborn.

Section 2 (Area 3-6) – ANN Hypothetical Concepts

This part will give you a strong comprehension of ideas engaged with Neural Organizations.

In this part you will find out about the single cells or Perceptrons and how Perceptrons are stacked to make an organization design. When design is set, we comprehend the Angle plummet calculation to discover the minima of a capacity and figure out how this is utilized to streamline our organization model.

Section 3 (Segment 7-11) – Making ANN model in Python

In this part you will figure out how to make ANN models in Python.

We will begin this part by making an ANN model utilizing Consecutive Programming interface to take care of an arrangement issue. We figure out how to characterize network engineering, arrange the model and train the model. At that point we assess the presentation of our prepared model and use it to anticipate on new information. In conclusion we figure out how to spare and reestablish models.

We likewise comprehend the significance of libraries, for example, Keras and TensorFlow in this part.

Section 4 (Segment 12) – CNN Hypothetical Ideas

In this part you will find out about convolutional and pooling layers which are the structure squares of CNN models.

In this part, we will begin with the fundamental hypothesis of convolutional layer, step, channels and highlight maps. We likewise clarify how dim scale pictures are unique in relation to shaded pictures. Ultimately we examine pooling layer which get computational effectiveness our model.

Section 5 (Area 13-14) – Making CNN model in Python

In this part you will figure out how to make CNN models in Python.

We will take a similar issue of perceiving style protests and apply CNN model to it. We will look at the exhibition of our CNN model with our ANN model and notice that the precision increments by 9-10% when we use CNN. Nonetheless, this isn’t its finish. We can additionally improve exactness by utilizing certain methods which we investigate in the following part.

Section 6 (Area 15-18) – Start to finish Picture Acknowledgment venture in Python

In this segment we assemble a total picture acknowledgment venture on hued pictures.

We take a Kaggle picture acknowledgment rivalry and manufacture CNN model to settle it. With a basic model we accomplish almost 70% exactness on test set. At that point we learn ideas like Information Expansion and Move Realizing which assist us with improving precision level from 70% to almost 97% (comparable to the champs of that opposition).

Before the finish of this course, your trust in making a Convolutional Neural Organization model in Python will take off. You’ll have a careful comprehension of how to utilize CNN to make prescient models and tackle picture acknowledgment issues.

Feel free to tap the select catch, and I’ll see you in exercise 1!

Good wishes

Start-Tech Institute

  • The following are some well known FAQs of understudies who need to begin their Profound learning venture

Why use Python for Profound Learning?

Understanding Python is one of the important aptitudes required for a profession in Profound Learning.

In spite of the fact that it hasn’t generally been, Python is the programming language of decision for information science. Here’s a short history:

In 2016, it overwhelmed R on Kaggle, the chief stage for information science rivalries.

In 2017, it overwhelmed R on KDNuggets’ yearly survey of information researchers’ most utilized devices.

In 2018, 66% of information researchers detailed utilizing Python day by day, making it the main instrument for investigation experts.

Profound Learning specialists anticipate that this pattern should proceed with expanding improvement in the Python biological system. And keeping in mind that your excursion to learn Python programming might be simply starting, it’s ideal to realize that business openings are plentiful (and developing) also.

What is the distinction between data Mining, AI, and Profound Learning?

Set forth plainly, AI and information mining utilize similar calculations and procedures as information mining, aside from the sorts of expectations fluctuate. While data mining finds in advance dark models and data, artificial intelligence copies known models and data—and further normally applies that information to data, dynamic, and exercises.

Profound learning, then again, utilizes progressed registering force and unique sorts of neural organizations and applies them to a lot of information to learn, comprehend, and recognize muddled examples. Programmed language interpretation and clinical determinations are instances of profound learning.


  • 19 sections • 53 lectures • 7h 0m total length

Introduction2 lectures • 4min

  • IntroductionPreview03:29
  • Course resources00:03

Setting up Python and Jupyter Notebook9 lectures • 1hr 38min

  • Installing Python and AnacondaPreview03:04
  • Opening Jupyter NotebookPreview09:06
  • Introduction to Jupyter13:26
  • Arithmetic operators in Python: Python Basics04:28
  • Strings in Python: Python Basics19:07
  • Lists, Tuples and Directories: Python Basics18:41
  • Working with Numpy Library of Python11:54
  • Working with Pandas Library of Python09:15
  • Working with Seaborn Library of Python08:57

Single Cells – Perceptron and Sigmoid Neuron3 lectures • 31min

  • Perceptron09:47
  • Activation Functions07:30
  • Python – Creating Perceptron model14:10

Neural Network – Stacking cells to create network 3 lectures • 44min

  • Basic Terminologies09:47
  • Gradient Descent12:17
  • Back Propagation22:27
  • Quiz1 question

Important concepts: Common Interview questions1 lecture • 13min

  • Some Important Concepts12:44
  • Quiz1 question

Standard Model Parameters1 lecture • 8min

  • Hyperparameters08:19

Tensorflow and Keras2 lectures • 7min

  • Keras and Tensorflow03:04
  • Installing Tensorflow and Keras04:04

Python – Dataset for classification problem 2 lectures • 12min

  • Dataset for classification07:20
  • Normalization and Test-Train split05:59

Python – Building and training the Model4 lectures • 33min

  • Different ways to create ANN using Keras01:58
  • Building the Neural Network using Keras12:24
  • Compiling and Training the Neural Network model10:34
  • Evaluating performance and Predicting using Keras09:21

Saving and Restoring Models1 lecture • 20min

  • Saving – Restoring Models and Using Callbacks19:49

Hyperparameter Tuning1 lecture • 9min

  • Hyperparameter Tuning09:05

CNN – Basics6 lectures • 36min

  • CNN Introduction07:43
  • Stride02:51
  • Padding05:07
  • Filters and Feature maps07:48
  • Channels06:31
  • PoolingLayer05:32
  • Quiz1 question

Creating CNN model in Python3 lectures • 19min

  • CNN model in Python – Preprocessing05:42
  • CNN model in Python – structure and Compile06:24
  • CNN model in Python – Training and results06:50

Analyzing impact of Pooling layer1 lecture • 6min

  • Comparison – Pooling vs Without Pooling in Python06:20

Project : Creating CNN model from scratch5 lectures • 29min

  • Project – Introduction07:05
  • Data for the project00:01
  • Project – Data Preprocessing in Python09:19
  • Project – Training CNN model in Python09:05
  • Project in Python – model results03:07

Project : Data Augmentation for avoiding overfitting2 lectures • 13min

  • Project – Data Augmentation Preprocessing06:46
  • Project – Data Augmentation Training and Results06:26

Transfer Learning : Basics5 lectures • 16min

  • ILSVRC04:10
  • LeNET01:31
  • VGG16NET02:00
  • GoogLeNet02:52
  • Transfer Learning05:15

Transfer Learning in Python1 lecture • 20min

  • Project – Transfer Learning – VGG1619:40

Bonus Section1 lecture • 1min

  • Congratulations & About your certificate00:35


Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker