PyTorch and fastai have two main classes for representing and accessing a training set or validation set: Dataset:: A collection that returns a tuple of your independent and dependent variable for a single itemDataLoader:: An iterator that provides a stream of mini-batches, where each mini-batch is a tuple of a batch of independent variables and … Continue reading FastAI: Multi-Label Classification [Chapter-6]
FastAI – Image Classification – [Chapter 5]
DataLoaders DataLoaders - Is a class that just stores whatever DataLoader object you pass to it and makes it available as train and valid. To turn downloaded data into a DataLoaders object we need at least 4 things - What kind of data we are working withHow to get the list of itemsHow to label … Continue reading FastAI – Image Classification – [Chapter 5]
FastAI : Training a Digit Classifier - [Chapter-4] - Part II
Metric is to drive human understanding and the loss is to drive automated learning. Stochastic Gradient Descent - As Arthur Samuel had mentioned the description of machine learning Suppose we arrange for some automatic means of testing the effectiveness of any current weight assignment in terms of actual performance and provide a mechanism for altering … Continue reading FastAI : Training a Digit Classifier - [Chapter-4] - Part II
fastai : Training a Digit Classifier - Baseline Model [Chapter-4] - Part I
Chapter 1 Notes - https://aprakash.wordpress.com/2021/07/05/fastai-just-go-out-and-play-chapter-1/ I want to start this blog with some of my personal notes before jumping on the book. Below is the notebook with examples of 1-dimensional, 2-dimensional and 3-dimensional array using numpy. 2. What is a norm? A norm is a measure of distance and have three properties All distances are … Continue reading fastai : Training a Digit Classifier - Baseline Model [Chapter-4] - Part I
Sequential counter with groupby – Pandas DataFrame
Pandas DataFrame is a 2-dimensional tabular data structure with labeled axes. For this blog, we have a table "person" in database containing name, age and city column. As dml transactions are performed on this table, the new image of the record along with the dml operation type is captured and stored in json file. The … Continue reading Sequential counter with groupby – Pandas DataFrame
Pandas Scratchpad – I
This blog is scratchpad for day-to-day Pandas commands. pandas is an open-source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language. 1. Few quick ways to create Pandas DataFrame DataFrame from Dict of List - DataFrame from List of List - DataFrame from List of Dict - DataFrame … Continue reading Pandas Scratchpad – I
Learn. Share. Repeat. 