Dr. Varshita Sher

Pinned

Building an efficient ‘hardware-aware’ object detection model in under 10 mins

Optimize model, compress model, search hyperparameters, pip package — all with just a few clicks. — What are hardware-aware models? Often times when data scientists think of an optimized model, they think in terms of one or the other metrics — such as accuracy, precision, recall, etc. In other words, efforts are made to ensure every last bit of accuracy is squeezed out of the training set by tuning the…

Deep Learning

12 min read

Building an efficient ‘hardware-aware’ object detection model in under 10 mins

Deep Learning

12 min read

Published in Towards Data Science

·Pinned

Detect emotion in speech data: Fine-tuning HuBERT using Huggingface

Building custom data loader, experiment logging, tips for improving metrics, and GitHub repo if you’d like to follow along — Why Audio Data? NLP for audio data is not getting enough recognition, compared to NLP for text and computer vision tasks. Time to change that! Task Emotion recognition — recognize whether spoken audio exhibits anger, happiness, sadness, disgust, surprise, or neutral emotions.

Hugging Face

15 min read

Hugging Face

15 min read

Published in Towards Data Science

·Pinned

How to Make the Most of Your Python Debugger in VSCode

Watch variables, use conditional breakpoints, call stack, exception breakpoint, etc— when working on larger projects — Quick pulse check — Still using print() statements to debug your code? Hey, no shame in admitting if you do. If it works, it works (especially for smaller scripts)! Having said that, it’s not a sustainable solution when working with larger projects — involving a buttload of third-party packages, util…

Vscode

13 min read

Vscode

13 min read

Published in Towards Data Science

·Pinned

Data scientist’s guide to efficient coding in Python

Tips and tricks I use for writing clean codes on a day-to-day basis — In this article, I wanted to share a few tips for writing cleaner codes that I have absorbed in the last year — mainly from pair programming. …

Python

11 min read

Python

11 min read

Published in Towards Data Science

·Pinned

Time Series Analysis using Pandas in Python

Bonus intro to keywords like seasonality, trend, autocorrelation, and much more. — Right off the bat, time-series data is not your average dataset! You might have worked with housing data wherein each row represents features of a particular house (such as total area, number of bedrooms, year in which it was built) or student dataset wherein each row represents such…

Time Series Analysis

14 min read

Time Series Analysis

14 min read

3 days ago

Using Causal ML Instead of A/B Testing

202

Samuele Mazzanti

Thanks, Samuele.

Thanks, Samuele. This is brilliant. Clearly the cut off assumption plays a big role here in generating the predictor matrix. Do you have any recommendations in this regard - perhaps trying a bunch of cut offs, averaging, etc and the impact on the outcome, if any?

1 min read

Nov 11

Why use `mono=False` when loading the audio with librosa?

Cleo Lafayette

That's cause we don't want to average samples across different channels (and risk losing some…

That's cause we don't want to average samples across different channels (and risk losing some signal in data) and ultimately convert the audio into 1-D array (especially when HuBERT can handle multi-dimensional audio arrays).

1 min read

Oct 13

Thank you so much. It is really helpful.

Sneha T

Hi Sneha, Please see the following articles wherein I have deployed the ML model on Heroku

Hi Sneha, Please see the following articles wherein I have deployed the ML model on Heroku - End to End Deep Learning Project, Part 1 and Part 2 Hope this helps!

1 min read

Hi Sneha, Please see the following articles wherein I have deployed the ML model on Heroku

- End to End Deep Learning Project, Part 1 and Part 2

Hope this helps!

Published in Towards Data Science

·Sep 6

How to turn your local (zip) data into a Huggingface Dataset

Quickly load your dataset in a single line of code for training a deep learning model — GitHub - V-Sher/HF-Loading-Script: How to write a custom loading script for HuggingFace datasets You can't perform that action at this time. You signed in with another tab or window. You signed out in another tab or…github.com What’s Huggingface 🤗 Dataset? If you have been working for some time in the field of deep learning (or even if you have only recently delved into it), chances are, you would have come across Huggingface — an open-source ML library that is a holy grail for all things AI (pretrained models, datasets, inference…

Hugging Face

11 min read

Hugging Face

11 min read

Published in Towards Data Science

·Jun 30

Hands-On Introduction to Github Actions for Data Scientists

Learn how to automate experiment tracking with Weights & Biases, unit testing, artifact creation, and lots more… — Why Github Actions? In layman's terms, Github Actions lets you automate a few routine and repetitive tasks — be it testing code every time it is deployed on the production branch, checking for good coding practices on PRs, cross-browser code testing, unit-testing, retrieving runs from MLFlow/WandB tracking, automatically closing stale issues, etc. …

Github Actions

14 min read

Github Actions

14 min read