Share this page!

Philip Vollet Profile picture
Twitter logo
26 Apr, 4 tweets, 1 min read
StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery - A text-based interface for StyleGAN image manipulation.

Abs arxiv.org/abs/2103.17249
GitHub github.com/orpatashnik/St… Image
They first introduce an optimization scheme that utilizes a CLIP-based loss to modify an input latent vector in response to a user-provided text prompt.
Next, they describe a latent mapper that infers a text-guided latent manipulation step for a given input image, allowing faster and more stable textbased manipulation.
Finally, they present a method for mapping a text prompts to input-agnostic directions in StyleGAN’s style space, enabling interactive text-driven image manipulation.

• • •

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

Keep Current with Philip Vollet

Philip Vollet 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 @philipvollet

Philip Vollet Profile picture
28 Apr
One of the best videos I know when it comes to putting NLP into production.

With the power of spaCy v3 and the underlying thinc library for robustness and reproducibility btw. the declarative config system is unbeaten.

@explosion_ai

↓ 1/4 Image
Learn more about spaCy v3.0 and its new features like: transformer-based pipelines, the new training config and workflow system to help you take projects from prototype to production.

STEP BY STEP

↓ 2/4
01:54​ – State-of-the-art transformer-based pipelines
05:03​ – Declarative configuration system
11:06​ – Workflows for end-to-end projects
17:03​ – Trainable and rule-based components
21:43​ – Custom models in any framework
26:20​ – Features and summary

↓ 3/4
Read 4 tweets
Philip Vollet Profile picture
24 Apr
Why is machine learning so important for healthcare?

A short thread on topic.

Let's look at Multiple Sclerosis!

1/6
Multiple Sclerosis is an umbrella term

What does that mean?

MS is a disease with different subtypes, symptomatology and manifestations.

2/6
As different as these can be, so different should be the treatment.

Why?
Based on the subtype differentiation, treatment options should be considered. MS treatment and patient response could be very different.

How did ML help here?

3/6
Read 6 tweets
Philip Vollet Profile picture
23 Apr
Opyrator - Turns your Python functions into microservices with web API and interactive GUI.

GitHub github.com/ml-tooling/opy…

$ 𝚙𝚒𝚙 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚘𝚙𝚢𝚛𝚊𝚝𝚘𝚛
Instantly turn your Python functions into production-ready microservices.

Deploy and access your services via HTTP API or interactive UI.
Seamlessly export your services into portable, shareable, and executable files or Docker images.

Opyrator builds on open standards - OpenAPI, JSON Schema, and Python type hints - and is powered by FastAPI @tiangolo
@streamlit & Pydantic
Read 4 tweets
Philip Vollet Profile picture
21 Apr
Using machine learning to understand whales?

The past decade has witnessed a groundbreaking rise of machine learning for human language analysis, with current methods capable of automatically accurately recovering various aspects of syntax and semantics - including sentence Image
structure and grounded word meaning - from large data collections.

Recent research showed the promise of such tools for analyzing acoustic communication in nonhuman species.
They posit that machine learning will be the cornerstone of future collection, processing, and analysis of multimodal streams of data in animal communication studies, including bioacoustic, behavioral, biological, and environmental data.
Read 6 tweets
Philip Vollet Profile picture
20 Apr
Machine learning from development into production as a team

What about
• Dependencies?
• Reproducibility?
• Continuous integration?

Save the hustle with these simple practices

↓ 1/6
Usually you start with a Jupyter notebook to make them robust especially working as a team nbdev is a life saver

GitHub github.com/fastai/nbdevq

↓ 2/6
nbdev is a library that allows you to develop a python library in Jupyter Notebooks, putting all your code, tests and documentation in one place. That is: you now have a true literate programming environment, as envisioned by Donald Knuth back in 1983!

↓ 3/6
Read 8 tweets
Philip Vollet Profile picture
19 Apr
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data? • Large Transformers pretrained over clinical notes from Electronic Health Records (EHR) have afforded substantial gains in performance on predictive clinical tasks.

Paper arxiv.org/abs/2104.07762
GitHub

↓ 1/4
github.com/elehman16/expo…

The cost of training such models and the necessity of data access to do so is coupled with their utility motivates parameter sharing, i.e., the release of pretrained models such as ClinicalBERT.

↓ 2/4
While most efforts have used deidentified EHR, many researchers have access to large sets of sensitive, non-deidentified EHR with which they might train a BERT model (or similar).

Would it be safe to release the weights of such a model if they did?

↓ 3/4
Read 4 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

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

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

Like this author's thread?

Get emails when @philipvollet has new unrolls!

Check out other threads from @philipvollet!

Read all threads by @philipvollet