PyTorch is one of the big frameworks to create Machine Learning models. In this lesson we will create a Deep Neural Network to classify images.
First we will explore how PyTorch differs from Tensorflow (another big framework). A way to explore that we will create a model to classify handwritten numbers.
In the project we will use our PyTorch to classify images from CIFAR-10.
Machine Learning with Python is a complete 10 hours course to get you started with Machine Learning. All you need to know to master all aspects of Machine Learning.
L E S S O N O B J E C T I V E S
• What is PyTorch
• PyTorch vs Tensorflow
• Get started with PyTorch
• Work with image classification with handwriting detection
• Make a project with detecting birds and airplanes pictures.
F U L L C O U R S E
The course is structured in 15 lessons with 15 projects covering all models: k-Nearest-Neighbors Classifier, Linear Classifier, Support Vector Classification, Linear Regression, Reinforcement Learning, Unsupervised Learning, Neural Networks, Deep Neural Networks (DNN), Convolutional, Neural Networks (CNN), PyTorch classifier, Recurrent Neural Networks (RNN), Natural Language Processing, Text Categorization, Information Retrieval, Information Extraction.
T I M E S T A M P S
00:00 Introduction
01:12 Goal of lesson
01:37 PyTorch free book
02:25 PyTorch and Tensorflow
03:33 Installing PyTorch and datasets
06:00 How to use PyTorch
08:33 Programming notes
09:25 Installing PyTorch, imports and downloads
10:38 Explore the dataset
11:40 Convert the dataset to tensors
12:50 Normalize the dataset
16:40 Create the model
20:20 Optimize the model
21:45 Calculate the accuracy
24:42 Project Description
30:05 Project Solution
30:17 Step 1: Install PyTorch
30:29 Step 2: Import libraries
30:33 Step 3: Download the CIFAR10 dataset
31:00 Step 4: Explore the dataset
32:20 Step 5: Visualize the image
32:40 Step 6: Transform images
33:45 Step 7: Normalize images
35:50 Step 8: Normalize the data
37:25 Step 9: Limit the dataset
38:57 Step 10: Create the model
40:19 Step 11: Train the model
42:28 Step 12: Test the model
43:02 Step 13 (Optional): Improve the model
43:34 Conclusion and next lesson
C O U R S E R E S O U R C E S
▸ Course Page: https://www.learnpythonwithrune.org/machine-learning/
▸ GitHub (Notebooks): https://github.com/LearnPythonWithRune/MachineLearningWithPython
D E S C R I P T I O N
• Machine Learning with Python - A beginners course covering all you need
• A 10 hour full course with Python for Machine Learning.
• Including Jupyter Notebooks and projects.
C O U R S E L E A R N I N G O B J E C T I V E S
• Create 15 projects with Machine Learning.
• k-Nearest-Neighbors Classifier
• Linear Classifier
• Support Vector Classification
• Linear Regression
• Reinforcement Learning
• Unsupervised Learning
• Neural Networks
• Deep Neural Networks (DNN)
• Convolutional Neural Networks (CNN)
• PyTorch classifier
• Recurrent Neural Networks (RNN)
• Natural Language Processing
• Text Categorization
• Information Retrieval
• Information Extraction
S T A Y C O N N E C T E D
▸ Facebook: https://www.facebook.com/learnpythonwithrune
▸ Twitter: https://twitter.com/PythonWithRune
▸ Blog: http://learnpythonwithrune.org
▸ Online courses: https://www.learnpythonwithrune.org/my-online-courses/
0 Comments