Deep Learning With PyTorch

Start solving Computer Vision problems using Deep Learning techniques and the PyTorch framework. Dive into the architecture of Neural Networks, and learn how to train and deploy them on the cloud.

Download Curriculum
Play Video

Course Code
DLPT

Type
Intermediate

Available in
Python

Price
$799

Prerequisites: Basic understanding of Computer Vision required
(Courses are (a little) oversubscribed and we apologize for your enrollment delay. As an apology, you will receive a 20% discount on all waitlist course purchases. The current wait time will be sent to you in the confirmation email.)
Play Video

Lifetime Access

Official OpenCV Certification

Active Community Support

30-Day Money-Back Guarantee

A glimpse of the topics covered

Course Topics

  1. Introduction to Artificial Intelligence
  2. NumPy Refresher
  3. Introduction to PyTorch
  4. What is inside an ML algorithm?
  1. Neural Network Building Blocks
  2. Loss Functions for Classification & Regression
  3. Understanding the PyTorch NN module
  4. Image Classification using Multilayer Perceptron
  1. The Convolution operation
  2. CNN building blocks and Layers
  3. Implement CNNs using PyTorch
  4. Evaluation of Classification Performance
  1. Torchvision Datasets
  2. Torchvision Transforms
  3. Important CNN Models
  4. Data Augmentation in Torchvision
  1. Optimizers in PyTorch
  2. Learning Rate Decay methods
  3. Training Deep Neural Networks
  4. Regularization methods in Deep Learning
  1. Troubleshooting training with TensorBoard
  2. Leverage pre-trained models
  3. How to structure your project for scale
  4. Custom Data Loaders
  1. Introduction to Object Detection
  2. Object Detection building blocks
  3. Evaluation Metrics in Object Detection like mAP
  4. Two-Stage Object Detectors like Faster RCNN
  1. You Only Look Once (YOLO)
  2. Single Stage Multibox Detector (SSD)
  3. Detectron 2 based Object Detection
  4. How to write a custom Object Detector from scratch
  1. Semantic Segmentation building blocks 
  2. Dilated Convolution and Transposed Convolution
  3. Semantic and Instance Segmentation
  4. Evaluation metrics for Semantic Segmentation
  1. Fully Convolutional Network (FCN)
  2. U-Net
  3. DeepLab
  4. Mask-RCNN
  1. Pose Estimation using DensePose
  2. Pose Estimation using YOLO Pose models
  3. Create your own Gym Trainer
  1. Introduction to GANs
  2. Vanilla GAN using Fashion MNIST
  3. DCGAN using Flickr Faces
  4. CGAN using Fashion MNIST

Tool Kit

Testimonials

Certificates

To receive a Certificate of Completion from OpenCV.org, you need to complete the graded quizzes + assignments + projects, with more than 50% marks and within 6 months of enrolling in the course.

Graduation Certificate

Certificate of Completion

You will receive a Certificate of Excellence if you score more than 70% marks on the graded quizzes + assignments + projects within 6 months of enrolling in the course.

Honor Certificate

Certificate of Excellence

This course is available as part of the following Programs


Course

Mastering OpenCV with

Python (Python) - $149

Fundamentals of Computer

Vision & Image Processing
(Python or C++) - $499

Deep Learning with

PyTorch (Python) - $799

Deep Learning with TensorFlow & Keras (Python) - $799

Computer Vision & Deep Learning Applications (Python) - $499

Mastering Generative AI

for Art (Python) - $159

Standard Retail

Special Pricing

Student Pricing (30% Discount)

Program 1
CVDL Essentials

$899

$629

Program 2
CVDL Professional

$1,199

$839

Program 3
CVDL Expert

$1,699

$1,189

Program 4
CVDL Master

$1,999

$1,399

Program 1
CVDL
Essentials
$629
$899
$899$584
Program 2
CVDL
Professional
$839
$1,199
$1199$779
Program 3
CVDL
Expert
$1189
$1,699
$1699$1104
Program 4
CVDL
Master
$1399
$1,999
$1999$1299
MOCV - Mastering OpenCV with Python - $149
CVIP - Fundamentals of CV & IP - (Python & C++) - $499
DLPT - Deep Learning With PyTorch - $799
DLTK - DL with TensorFlow & Keras -$799
DLAP - CV & DL Applications - $499
GENAI - Mastering Generative AI for Art - $159

Courses Offered

Edit Content