NVIDIA DLI WORKSHOP


ABOUT

Date: 28th December 2017
Venue: LA 101
Reporting Time: 8am
Time: 9am-5pm


NVIDIA offers hands-on training for developers, data scientists, and researchers looking to solve the world’s most challenging problems with deep learning.

DETAILS

Date : 28th December 2017

Duration: 1 Day (8 Hour Workshop)

Venue: IIT Bombay

Cost of Workshop:₹ 1,500/- per person

No. of Team Members: 1

Refund Deadline: 1st November 2017, No Refunds will be entertained after the Deadline.

**Limited number of seats

**If the Workshop gets cancelled, all the participants will be given full refund, irrespective of the Deadline.

CONTENT

9.00 am to 9.45 am : Deep Learning Demystified and Applied Deep Learning (lecture)

10 am to 12.00 am: Image Classification with DIGITS (lab)

Frameworks: Caffe
This lab shows you how to leverage deep neural networks (DNN) - specifically convolutional neural networks (CNN) - within the deep learning workflow to solve a real-world image classification problem using NVIDIA DIGITS on top of the Caffe framework and the MNIST hand-written digits dataset. In this lab, you will learn how to:

  • Architect a Deep Neural Network to run on a GPU
  • Manage the process of data preparation, model definition, model training and troubleshooting
  • Use validation data to test and try different strategies for improving model performance
  • On completion of this lab, you will be able to use NVIDIA DIGITS to architect, train, evaluate and enhance the accuracy of CNNs on your own image classification application.

12:00pm Lunch

1:00pm Object Detection with DIGITS (LAB)

This lab explores three approaches to identify a specific feature within an image. Each approach is measured in relation to three metrics: model training time, model accuracy and speed of detection during deployment. On completion of this lab, you will understand the merits of each approach and learn how to detect objects using neural networks trained on NVIDIA DIGITS on real-world datasets.
3:00 pm Break

3:15 pm Neural Network Deployment with DIGITS and TensorRT (lab)

Frameworks: Caffe
In this lab, you will learn how to:
  • Understand the role of batch size in inference performance
  • Make various optimizations in the inference process.
  • Explore inference for a variety of different DNN architectures trained in other DLI labs.
  • On completion of this lab, you will be able to execute a full Deep Learning workflow: from loading data, to training a neural network, to deploying that trained network to production.

5:15 pm Closing Comments & Questions

5:30 pm End

For more detail Content Click Here

RULES

Eligibility :
Participants having a valid ID card of their respective educational institutions are eligible for the workshop.

Team specifications :
Participants will have to register individually.

Prerequisites :
Each participant should bring one laptop and a dongle/Jio with them. ( We will be providing internet but it is requested to bring yours for better experience)

Certificate criterion :
Participants should be present in all the sessions. Failing this, no certificate will be awarded to the participant.

CONTACT US

Shashank Sahu
shashank@techfest.org

Date :
28th December 2017

NVIDIA DLI


ABOUT

Date: 28th December 2017
Venue: LA 101
Reporting Time: 8am
Time: 9am-5pm


NVIDIA offers hands-on training for developers, data scientists, and researchers looking to solve the world’s most challenging problems with deep learning.

DETAILS

Date: 28th December 2017

Duration: 1 Day (8 hour workshop)

Venue: IIT Bombay

Cost of Workshop:₹ 1,500/- per person

No. of Team Members: 1

Refund Deadline: 1st November 2017, No Refunds will be entertained after the Deadline.

**Limited number of seats

**If the Workshop gets cancelled, all the participants will be given full refund, irrespective of the Deadline.

CONTENT

    9.00 am to 9.45 am : Deep Learning Demystified and Applied Deep Learning (lecture)

    10 am to 12.00 am: Image Classification with DIGITS (lab)

    Frameworks: Caffe
    This lab shows you how to leverage deep neural networks (DNN) - specifically convolutional neural networks (CNN) - within the deep learning workflow to solve a real-world image classification problem using NVIDIA DIGITS on top of the Caffe framework and the MNIST hand-written digits dataset. In this lab, you will learn how to:
    • Architect a Deep Neural Network to run on a GPU
    • Manage the process of data preparation, model definition, model training and troubleshooting
    • Use validation data to test and try different strategies for improving model performance
    • On completion of this lab, you will be able to use NVIDIA DIGITS to architect, train, evaluate and enhance the accuracy of CNNs on your own image classification application.

    12:00pm Lunch

    1:00pm Object Detection with DIGITS (LAB)

    This lab explores three approaches to identify a specific feature within an image. Each approach is measured in relation to three metrics: model training time, model accuracy and speed of detection during deployment. On completion of this lab, you will understand the merits of each approach and learn how to detect objects using neural networks trained on NVIDIA DIGITS on real-world datasets.
    3:00 pm Break

    3:15 pm Neural Network Deployment with DIGITS and TensorRT (lab)

    Frameworks: Caffe
    In this lab, you will learn how to:
    • Understand the role of batch size in inference performance
    • Make various optimizations in the inference process.
    • Explore inference for a variety of different DNN architectures trained in other DLI labs.
    • On completion of this lab, you will be able to execute a full Deep Learning workflow: from loading data, to training a neural network, to deploying that trained network to production.

    5:15 pm Closing Comments & Questions

    5:30 pm End

    For more detail Content Click Here

RULES

    Eligibility :
    Participants having a valid ID card of their respective educational institutions are eligible for the workshop.

    Team specifications :
    Participants will have to register individually.

    Prerequisites :
    Each participant should bring one laptop and a dongle/Jio with them. (We will be providing internet but it is requested to bring yours for better experience)

    Certificate criterion :
    Participants should be present in all the sessions. Failing this, no certificate will be awarded to the participant.

Shashank Sahu
shashank@techfest.org
+91 9630809789
Div Six

Explore More

CLOSED !

×
×