How to build custom Datasets for Text in Pytorch

Aladdin Persson · Beginner ·📐 ML Fundamentals ·5y ago
In this video we go through a bit more in depth into custom datasets and implement more advanced functions for dealing with text. Specifically we're looking at a image captioning dataset (Flickr8k data set) with an image and a corresponding caption text that describes what's going on in the image. I think the general principles from this video can be utilized to any project you're working with when dealing with text data be it either translation, question answering, sentiment analysis etc. I also recommend taking a look at my Torchtext which can also be quite helpful and simplify the data load…
Watch on YouTube ↗ (saves to browser)

Chapters (9)

Introduction
2:05 Overview of what we're going to do
4:05 Imports
5:20 Setup of Pytorch Dataset for loading Flickr
11:50 Setup of Vocabulary and Numericalization
22:19 Creating Collate for Padding of Batch
25:20 Function for getting data loader
29:15 Running code & fixing couple of errors
33:09 Ending

Playlist

Uploads from Aladdin Persson · Aladdin Persson · 0 of 60

← Previous Next →
1 computeCost.m Linear Regression Cost Function - Machine Learning
computeCost.m Linear Regression Cost Function - Machine Learning
Aladdin Persson
 2 gradientDescent.m Gradient Descent Implementation - Machine Learning
gradientDescent.m Gradient Descent Implementation - Machine Learning
Aladdin Persson
 3 Neural Network from scratch - Part 1 (Standard Notation)
Neural Network from scratch - Part 1 (Standard Notation)
Aladdin Persson
 4 Neural Network from scratch - Part 2 (Forward Propagation)
Neural Network from scratch - Part 2 (Forward Propagation)
Aladdin Persson
 5 Neural Network from scratch - Part 3 (Backward Propagation)
Neural Network from scratch - Part 3 (Backward Propagation)
Aladdin Persson
 6 Neural Network from scratch - Part 4 (With Python)
Neural Network from scratch - Part 4 (With Python)
Aladdin Persson
 7 sigmoid.m - Programming Assignment 2 Machine Learning
sigmoid.m - Programming Assignment 2 Machine Learning
Aladdin Persson
 8 costFunction.m - Programming Assignment 2 Machine Learning
costFunction.m - Programming Assignment 2 Machine Learning
Aladdin Persson
 9 predict.m - Programming Assignment 2 Machine Learning
predict.m - Programming Assignment 2 Machine Learning
Aladdin Persson
 10 costFunctionReg.m - Programming Assignment 2 Machine Learning
costFunctionReg.m - Programming Assignment 2 Machine Learning
Aladdin Persson
 11 lrCostFunction.m - Programming Assignment 3 Machine Learning
lrCostFunction.m - Programming Assignment 3 Machine Learning
Aladdin Persson
 12 oneVsAll.m - Programming Assignment 3 Machine Learning
oneVsAll.m - Programming Assignment 3 Machine Learning
Aladdin Persson
 13 predictOneVsAll.m - Programming Assignment 3 Machine Learning
predictOneVsAll.m - Programming Assignment 3 Machine Learning
Aladdin Persson
 14 predict.m - Programming Assignment 3 Machine Learning
predict.m - Programming Assignment 3 Machine Learning
Aladdin Persson
 15 Caesar Cipher Encryption and Decryption with example
Caesar Cipher Encryption and Decryption with example
Aladdin Persson
 16 Cryptography: Caesar Cipher Python
Cryptography: Caesar Cipher Python
Aladdin Persson
 17 Vigenere Cipher Explained (with Example)
Vigenere Cipher Explained (with Example)
Aladdin Persson
 18 Cryptography: Vigenere Cipher Python
Cryptography: Vigenere Cipher Python
Aladdin Persson
 19 Hill Cipher Explained (with Example)
Hill Cipher Explained (with Example)
Aladdin Persson
 20 Cryptography: Hill Cipher Python
Cryptography: Hill Cipher Python
Aladdin Persson
 21 Interval Scheduling Greedy Algorithm: Python
Interval Scheduling Greedy Algorithm: Python
Aladdin Persson
 22 Weighted Interval Scheduling Algorithm Explained
Weighted Interval Scheduling Algorithm Explained
Aladdin Persson
 23 Weighted Interval Scheduling Python Code
Weighted Interval Scheduling Python Code
Aladdin Persson
 24 Sequence Alignment | Needleman Wunsch Algorithm
Sequence Alignment | Needleman Wunsch Algorithm
Aladdin Persson
 25 Sequence Alignment | Needleman Wunsch in Python
Sequence Alignment | Needleman Wunsch in Python
Aladdin Persson
 26 Codility BinaryGap Python
Codility BinaryGap Python
Aladdin Persson
 27 Codility CyclicRotation Python
Codility CyclicRotation Python
Aladdin Persson
 28 Derivation Linear Regression with Gradient Descent
Derivation Linear Regression with Gradient Descent
Aladdin Persson
 29 Linear Regression Gradient Descent From Scratch in Python
Linear Regression Gradient Descent From Scratch in Python
Aladdin Persson
 30 Pytorch Neural Network example
Pytorch Neural Network example
Aladdin Persson
 31 Pytorch CNN example (Convolutional Neural Network)
Pytorch CNN example (Convolutional Neural Network)
Aladdin Persson
 32 Pytorch LeNet implementation from scratch
Pytorch LeNet implementation from scratch
Aladdin Persson
 33 Pytorch VGG implementation from scratch
Pytorch VGG implementation from scratch
Aladdin Persson
 34 Pytorch GoogLeNet / InceptionNet implementation from scratch
Pytorch GoogLeNet / InceptionNet implementation from scratch
Aladdin Persson
 35 How to save and load models in Pytorch
How to save and load models in Pytorch
Aladdin Persson
 36 How to build custom Datasets for Images in Pytorch
How to build custom Datasets for Images in Pytorch
Aladdin Persson
 37 Pytorch Transfer Learning and Fine Tuning Tutorial
Pytorch Transfer Learning and Fine Tuning Tutorial
Aladdin Persson
 38 Pytorch Data Augmentation using Torchvision
Pytorch Data Augmentation using Torchvision
Aladdin Persson
 39 Pytorch Quick Tip: Weight Initialization
Pytorch Quick Tip: Weight Initialization
Aladdin Persson
 40 Pytorch Quick Tip: Using a Learning Rate Scheduler
Pytorch Quick Tip: Using a Learning Rate Scheduler
Aladdin Persson
 41 Pytorch ResNet implementation from Scratch
Pytorch ResNet implementation from Scratch
Aladdin Persson
 42 Pytorch TensorBoard Tutorial
Pytorch TensorBoard Tutorial
Aladdin Persson
 43 Pytorch DCGAN Tutorial (See description for updated video)
Pytorch DCGAN Tutorial (See description for updated video)
Aladdin Persson
 44 Naive Bayes from Scratch - Machine Learning Python
Naive Bayes from Scratch - Machine Learning Python
Aladdin Persson
 45 Spam Classifier using Naive Bayes in Python
Spam Classifier using Naive Bayes in Python
Aladdin Persson
 46 K-Nearest Neighbor from scratch - Machine Learning Python
K-Nearest Neighbor from scratch - Machine Learning Python
Aladdin Persson
 47 Linear Regression Normal Equation Python
Linear Regression Normal Equation Python
Aladdin Persson
 48 SVM from Scratch - Machine Learning Python (Support Vector Machine)
SVM from Scratch - Machine Learning Python (Support Vector Machine)
Aladdin Persson
 49 Neural Network from Scratch - Machine Learning Python
Neural Network from Scratch - Machine Learning Python
Aladdin Persson
 50 Pytorch RNN example (Recurrent Neural Network)
Pytorch RNN example (Recurrent Neural Network)
Aladdin Persson
 51 Pytorch Bidirectional LSTM example
Pytorch Bidirectional LSTM example
Aladdin Persson
 52 Pytorch Text Generator with character level LSTM
Pytorch Text Generator with character level LSTM
Aladdin Persson
 53 Logistic Regression from Scratch - Machine Learning Python
Logistic Regression from Scratch - Machine Learning Python
Aladdin Persson
 54 K-Means Clustering from Scratch - Machine Learning Python
K-Means Clustering from Scratch - Machine Learning Python
Aladdin Persson
 55 Pytorch Torchtext Tutorial 1: Custom Datasets and loading JSON/CSV/TSV files
Pytorch Torchtext Tutorial 1: Custom Datasets and loading JSON/CSV/TSV files
Aladdin Persson
 56 Pytorch Torchtext Tutorial 2: Built in Datasets with Example
Pytorch Torchtext Tutorial 2: Built in Datasets with Example
Aladdin Persson
 57 Pytorch Torchtext Tutorial 3: From Textfiles to Dataset
Pytorch Torchtext Tutorial 3: From Textfiles to Dataset
Aladdin Persson
 58 Paper Review: Sequence to Sequence Learning with Neural Networks
Paper Review: Sequence to Sequence Learning with Neural Networks
Aladdin Persson
 59 Pytorch Seq2Seq Tutorial for Machine Translation
Pytorch Seq2Seq Tutorial for Machine Translation
Aladdin Persson
 60 Pytorch Seq2Seq with Attention for Machine Translation
Pytorch Seq2Seq with Attention for Machine Translation
Aladdin Persson
The Hyper Moser (and other Mega Numbers) - Numberphile
Next Up
The Hyper Moser (and other Mega Numbers) - Numberphile
Numberphile