Share this page!

Full Stack Deep Learning Profile picture
Twitter logo
Nov 1 • 10 tweets • 4 min read
At FSDL, we believe in the power of shipping. So in the class, students build and share their own ML-powered products. This year, folks built all kinds of things, from a recipe inverter to a VTuber generator.

We'll be sharing some of our favorites here on Twitter.
Course Co-Pilot: convert a YT video into a text summary.

Team: @waydegilliam, @kurianbenoy2, @suvash

We look forward to using this to automate lecture note generation! Image
You can find a demo videos (and more!) for Course Co-Pilot and the rest of the projects on our course website:

fullstackdeeplearning.com/course/2022/pr…
Admirer: a visual Q&A system that hooks into your webcam.

Team: @ajhinh

Yep, one person built this! Really underscores just how much more effective MLE tooling has made developers. Image
Green-Screen Image Composition Transfer: better virtual backgrounds using style transfer.

Team: @Nitin_wysiwyg

Demo: huggingface.co/spaces/NikeZol…
Big midthread shout-out to @LambdaAPI, who donated the compute that many of these projects used for training and serving!
Weak Supervision and Active Learning with Text Data: using @SnorkelAI and Rubrix to cut down on human labeling costs and close the learning loop.

Team: Aleks Hiidenhovi, Bernardo García, Diego Quintana, Edoardo Abati, Juan Manuel, Kushal Ramaiya Image
X-Ray Diagnosis AI Assistant: a UI for using X-ray interpretation models, with explainability and attribution built in.

Team: Arun Hegde, Samarth Keshari, Amulya Badal, Ross Cheung, Seyhan Karakulak Image
Mom's AI Food Logger: replace a manual food-logging workflow with a computer vision system.

Team: Prince Javier

We love ML-powered products that are designed to solve a concrete user need! Image
You can find demo videos (and more!) for all of these projects on our course website:

fullstackdeeplearning.com/course/2022/pr…

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Full Stack Deep Learning

Full Stack Deep Learning Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @full_stack_dl

Full Stack Deep Learning Profile picture
Nov 3
In past threads, we've seen that our students this year built webcam-based visual Q&A, semantic search engines, and more.

In this final thread, we'll see the last few projects, from an iNaturalist-style plant identifer to a streaming art generator.
In-Browser AI: neural networks in the browser with the @onnxai web runtime.

Team: @visheratin

Check it out here: edge-ai.vercel.app Image
Audio VTuber: animate a "virtual YouTuber" to speak with your voice.

Team: Alex Service, Moon Ma

Try it here: audiovtuber.lol Image
Read 8 tweets
Full Stack Deep Learning Profile picture
Nov 3
We're sharing some of our favorite student projects from this year's cohort.

Read on for a sign language word detector, a semantic image blurring system, and more!
👻 Image Anonymiser: building on object detectors to selectively remove information from images.

Team: Sami Saadaoui, Vladislav Vancak, Lawrence Francis, Dan Howarth, Allan Stevenson

Really nice writeup here: saadaosa.github.io/ImageAnonymise… Image
BuggingSpace: an interface for "red-teaming" open source text generation models on @huggingface.

Team: Sashank Pisupati, Sajenthan Vigneswaran, Kemp Bray, Jean-Antoine Zagato

We love to see work on better evaluation of models!

Try it out yourself: huggingface.co/spaces/fsdlred…
Read 8 tweets
Full Stack Deep Learning Profile picture
Nov 2
We've tweeted a lot of threads on the FSDL 2022 labs, which build a simple demo OCR app from scratch.

It may not have been obvious from the outside, but these labs are designed to each be useful independently.

So we've collected them up into a 🧵 thread-of-threads 🧵.
(Pre)Labs 0-3 🧵: Overview, PyTorch, Lightning + CNNs, and Transformers
Lab 4 🧵: Experiment Management
Read 8 tweets
Full Stack Deep Learning Profile picture
Nov 2
In our last thread, we made it through the first few student projects, including a video summarizer and an X-ray reader.

Now, let's do a few more -- like the nanofiber measurer and the recipe inverter.
Archaeological Feature Detector: automatically detect and interpret evidence for remains of prehistoric structures in LIDAR data.

Team: Philanoe, jmmoreu, kempbray, lakillo (github u/ns)

We love to see interdisciplinary work! Image
Semantic Search Engine for Images: find images from a database using natural language descriptions.

Team: Sandhya Govindaraju, Utkarsh Vardhan, Gabriella Chiribau, Amit Kumar Sah

Really impressive monitoring setup too. Try it for yourself!

fsdl2022.plotto.info Image
Read 11 tweets
Full Stack Deep Learning Profile picture
Oct 31
Over the last few months of running the Full Stack Deep Learning course, we released one lecture video (+notes) each week and wrote an accompanying Twitter thread.

That's a lot of content, so here's a 🧵 thread-of-threads 🧵 collecting all of them up.
Lecture 1 🧵: Course Vision and When to Use ML, by @josh_tobin_
Lecture 2 🧵: Development Infrastructure & Tooling, by @sergeykarayev
Read 11 tweets
Full Stack Deep Learning Profile picture
Oct 26
🧪 Lab 5: Troubleshooting & Testing 🧪 didn't get a thread at time of release, so let's do one now!

For the testing part of the lab, we cover the basic tools with an eye on what works best for ML.

For example, Shellcheck to catch weird edge cases in the bash scripts that often glue ML pipeline steps together and fail silently with dire consequences:

shellcheck.net
We also go over Python linting tools like flake8 and black.

Tools are great, but tool management is not.

We recommend (and in the lab walk you through) using @pre_commit to manage and run your quality assurance tools.
Read 8 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

Send Email!

Email the whole thread instead of just a link!

Separate emails with commas

:(