zakruti.com » IT - Software » freeCodeCamp.org

Deep Learning with PyTorch Live Course - ResNet, Regularization and Data Augmentation (Part 5 of 6)

video description

Rating: 4.0; Vote: 1

This video covers the process of applying advanced techniques like residual networks, data augmentation, batch normalization and transfer learning to achieve state of the art results for image classification in a very short time. Resources: - Classifying CIFAR10 images using a ResNet : https://jovian.ml/aakashns/05b-cifar10-resnet - Transfer learning starter: https://jovian.ml/aakashns/transfer-learning-starter - Discussion forum: https://jovian.ml/forum/t/lecture-5-data-augmentation-regularization-and-resnets/1546 - Data science competition: https://www.kaggle.com/c/jovian-pytorch-z2g - Course project: https://jovian.ml/forum/t/assignment-5-course-project/1563 Topics covered: -- Improving the dataset using data normalization and data augmentation -- Improving the model using residual connections and batch normalization -- Improving the training loop using learning rate annealing, weight decay and gradient clip -- Training a state of the art image classifier from scratch in 5 minutes
Date: 2022-03-14

← Live Coding Project: Create a Random Quote Machine using Vue.js - with Gwen Faraday

Scikit-Learn Course - Machine Learning in Python Tutorial →

Related videos

AM4 Lives: AMD Ryzen 5 5500X3D CPU Review & Benchmarks

• Gamers Nexus

The ASUS Dumpster Fire

• Gamers Nexus

Windows Recall Is Too Risky, Turn It Off

• PC World

How to Extend Windows 10 Support For Free (Enroll Now)

• Geeks Tutorial

How to Create a Windows 11 Bootable USB Flash Drive Using Rufus

• Geeks Tutorial

End of Real Photography

• PiXimperfect

Comments and reviews: 4

Bernard
Thank you very much for this course! Could you provide the dataset used for the human protein image classification? (Or a script to generate it from the Human Protein Atlas Image Classification dataset?). At the moment, only invited users can download the dataset from kaggle.
reply

Beyond
Lecture is good but I'm very confused about layer dimensions
1) input dimensions
2) output dimensions
3) transformed dimensions by layers .
Can you please make cheatseet about all required repeated things ?
It's will much helpful for us
+1 -
reply

jdragon
so i have read and understood all these 5 lecture , what am i capable of now , i cant find anyone around me doing anything other than web dev . i need ml friends
reply

Chris
Thank you for this great course Are you going to do also a course about RNN Attentionlayers or other state of the art model That would be awesome :)
reply

Add a review, comment