Share this page!

Vladimir Haltakov Profile picture
Twitter logo
21 Dec, 5 tweets, 3 min read
Things are getting more and more interesting for AI-generated images! 🎨

GLIDE is a new model by @OpenAI that can generate images guided by a text prompt. It is based on a diffusion model instead of the more widely used GAN models.

Some details πŸ‘‡
@OpenAI GLIDE also has the interesting ability to perform inpainting allowing for some interesting usages.

πŸ‘‡
@OpenAI Here is the full paper

arxiv.org/abs/2112.10741

πŸ‘‡
@OpenAI Code and an (unfortunately small) pre-trained model on GitHub:

github.com/openai/glide-t…

πŸ‘‡
@OpenAI You can check out some people experimenting with it already under the #glide hashtag.

I'll play around with it as well in the next few days... πŸ˜€

β€’ β€’ β€’

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

Keep Current with Vladimir Haltakov

Vladimir Haltakov 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 @haltakov

Vladimir Haltakov Profile picture
17 Dec
How to evaluate your ML model? πŸ“

Your accuracy is 97%, so this is pretty good, right? Right? No! ❌

Just looking at the model accuracy is not enough. Let me tell you about some other metrics:
β–ͺ️ Recall
β–ͺ️ Precision
β–ͺ️ F1 score
β–ͺ️ Confusion matrix

Let's go πŸ‘‡

#RepostFriday
We'll use this example in the whole thread - classifying traffic light colors (e.g. for a self-driving car).

Yellow traffic lights appear much less often, so our dataset may look like this.

This means our model could reach 97% accuracy, by ignoring all 🟑 lights. Not good!

πŸ‘‡
Let's assume now that we trained our model and we get the following predictions.

Do you think this model is good? How can we quantitatively evaluate its performance? How should it be improved?

Let's first discuss the possible error types πŸ‘‡
Read 12 tweets
Vladimir Haltakov Profile picture
15 Dec
First officially approved Level 3 self-driving system in Germany.

This is significant because it is the first time an autonomous system that takes the *driving responsibility* from the driver is approved for mass production!

europe.autonews.com/automakers/mer…

πŸ‘‡
The main difference between Level 2 and Level 3 systems is that self-driving systems become legally responsible for the actions of the cars when in autonomous mode!

All driver assist systems on the market now (including Tesla) are Level 2 systems.



πŸ‘‡
While Waymo and Cruise have Level 4 systems running as a beta in some cities, there are different challenges putting this tech in consumer vehicles and in cars that don't have a huge sensor rack costing tens of thousands of dollars on the roof.

πŸ‘‡
Read 4 tweets
Vladimir Haltakov Profile picture
18 Nov
Let's talk about a common problem in ML - imbalanced data βš–οΈ

Imagine we want to detect all pixels belonging to a traffic light from a self-driving car's camera. We train a model with 99.88% performance. Pretty cool, right?

Actually, this model is useless ❌

Let me explain πŸ‘‡
The problem is the data is severely imbalanced - the ratio between traffic light pixels and background pixels is 800:1.

If we don't take any measures, our model will learn to classify each pixel as background giving us 99.88% accuracy. But it's useless!

What can we do? πŸ‘‡
Let me tell you about 3 ways of dealing with imbalanced data:

β–ͺ️ Choose the right evaluation metric
β–ͺ️ Undersampling your dataset
β–ͺ️ Oversampling your dataset
β–ͺ️ Adapting the loss

Let's dive in πŸ‘‡
Read 14 tweets
Vladimir Haltakov Profile picture
17 Nov
Machine Learning in the Real World 🧠 πŸ€–

ML for real-world applications is much more than designing fancy networks and fine-tuning parameters.

In fact, you will spend most of your time curating a good dataset.

Let's go through the steps of the process together πŸ‘‡
Collect Data πŸ’½

We need to represent the real world as accurately as possible. If some situations are underrepresented we are introducing Sampling Bias.

Sampling Bias is nasty because we'll have high test accuracy, but our model will perform badly when deployed.

πŸ‘‡
Traffic Lights 🚦

Let's build a model to recognize traffic lights for a self-driving car. We need to collect data for different:

β–ͺ️ Lighting conditions
β–ͺ️ Weather conditions
β–ͺ️ Distances and viewpoints
β–ͺ️ Strange variants

And if we sample only 🚦 we won't detect πŸš₯ πŸ€·β€β™‚οΈ

πŸ‘‡
Read 16 tweets
Vladimir Haltakov Profile picture
16 Nov
Can you detect COVID-19 using Machine Learning? πŸ€”

You have an X-ray or CT scan and the task is to detect if the patient has COVID-19 or not. Sounds doable, right?

None of the 415 ML papers published on the subject in 2020 was usable. Not a single one!

Let's see why πŸ‘‡
Researchers from Cambridge took all papers on the topic published from January to October 2020.

β–ͺ️ 2212 papers
β–ͺ️ 415 after initial screening
β–ͺ️ 62 chosen for detailed analysis
β–ͺ️ 0 with potential for clinical use

healthcare-in-europe.com/en/news/machin…

There are important lessons here πŸ‘‡
Small datasets 🐁

Getting medical data is hard, because of privacy concerns, and at the beginning of the pandemic, there was just not much data in general.

Many papers were using very small datasets often collected from a single hospital - not enough for real evaluation.

πŸ‘‡
Read 10 tweets
Vladimir Haltakov Profile picture
15 Nov
Mastering your Machine Learning Interview πŸ§‘β€πŸ«

I've summarized some great resources for you that will help you with your Machine Learning interview.

Read below πŸ‘‡
A great book by @chipro distilling a lot of information on preparing for a machine learning interview.

huyenchip.com/ml-interviews-…

Next πŸ‘‡
A collection of questions by @svpino who has a lot of experience interviewing people for ML positions.



Next πŸ‘‡
Read 9 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

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

Like this author's thread?

Get emails when @haltakov has new unrolls!

Check out other threads from @haltakov!

Read all threads by @haltakov

:(