SkalskiP @skalskip92 Twitter profile

Pinned Tweet

SkalskiP

@skalskip92

17 days

supervision - a computer vision library I created - just crossed 15,000 stars on GitHub! BBBRRRRRR! link:

50

598

6K

Last Seen Profiles

@honestbroham

@BitmapEmporium

@Bblinda_Silva3

@voetbalvolger13

@_MorrTex

@Manzanares_CF_

@MilkMeiStuff

@that_shutterbug

@alltoodaylight

@Valery33702

@comicsandfooty1

@Zeus_yucegod

@juan89113515

@MyllaFernandaa1

@KunshuLucas

@ghxclips

@KurtZouma

@tadaresan

@RobertoLai74153

@2000sfanatic

@GreyceIcaro

@USIFOH1515

@BohannanIowa

@kumapinkeu

@Quiniito10

@inosukeechann

@lyli_by

@AdrianMatyasik

@shealuxbeauty

@runningchannel

@FieldsToThePros

@camillefrases

@thetimewarbot

@LaryssaAnt

@hairyhillfarmer

@AidanWalshMUFC

SkalskiP

@skalskip92

13 days

polish TV is using computer vision to enhance the viewer experience for sports broadcasts: - FIFA-like radar overlays - player recognition - pass distance measurement - ball speed and trajectory tracking during shots

208

1K

14K

SkalskiP

@skalskip92

8 months

RIP image annotation companies Fully automated image labeling with GroundingDINO + SAM + OpenAI Vision API code:

65

395

3K

SkalskiP

@skalskip92

11 months

supervision-0.13.0 is out! Now you can effortlessly build advanced video analytics. Trackers, Zones, Annotators, and much more. GitHub repository:

36

546

3K

SkalskiP

@skalskip92

6 months

here is the final version of my vehicle speed estimation demo read the thread below to learn how I built it. I will cover: - detection - tracking - perspective transformation - speed calculation - some bonus ideas ↓

75

285

3K

SkalskiP

@skalskip92

5 months

REAL-TIME object detection WITHOUT TRAINING YOLO-World is a new SOTA open-vocabulary object detector that outperforms previous models in terms of both accuracy and speed. 35.4 AP with 52.0 FPS on V100. ↓ read more

35

383

3K

SkalskiP

@skalskip92

3 months

supervision, the open-source library I created a year ago, has crossed 10,000 stars on GitHub this weekend! thank you to everyone who helped me build this project! it took us 2,000+ commits, 500+ PRs and 50+ contributors to do it. repository:

21

313

2K

SkalskiP

@skalskip92

2 months

almost fully functional version of my football AI project today, I added player tracking using ByteTrack and projection of players onto the map code coming soon:

53

210

2K

SkalskiP

@skalskip92

11 months

supervision-0.13.0 is out! We added ByteTrack support! Now you can easily plug in any object detector and use it for tracking. GitHub repository:

46

311

2K

SkalskiP

@skalskip92

5 months

I'm starting to get more and more serious with YOLO-World; trying to solve real-life problems. I wanted to see if YOLO-World could recognize that the holes had been filled out. It was pretty tricky, but I learned a little about prompting. ↓ read more

16

168

1K

SkalskiP

@skalskip92

10 months

The traffic analysis project is growing! The YouTube tutorial will be out this week. Progress: I can now identify that the car is in a specified zone. Next: Match entrance and exit zones for every tracker ID to analyze the traffic flow. GitHub repo:

20

292

1K

SkalskiP

@skalskip92

8 months

Chat with the webcam using @OpenAI vision API

45

179

1K

SkalskiP

@skalskip92

2 months

I'm taking my football/soccer project to the next level today, I worked on detecting players, referees, and the ball and mapping their positions from video frames to positions on the field. ↓ read more

60

120

1K

SkalskiP

@skalskip92

1 month

I fine-tuned my first vision-language model PaliGemma is an open-source VLM released by @GoogleAI last week. I fine-tuned it to detect bone fractures in X-ray images. thanks to @mervenoyann and @__kolesnikov__ for all the help! ↓ read more

30

196

1K

SkalskiP

@skalskip92

10 months

ball and player 3d pose estimation - easily one of the coolest computer vision projects I have ever made repository:

24

184

1K

SkalskiP

@skalskip92

3 months

detecting AI-generated text researchers studied the impact of ChatGPT on AI conference peer reviews, confirming what we all knew paper: ↓ read more

32

118

1K

SkalskiP

@skalskip92

7 months

Nov 6th, 2023: We love you guys! Nov 17th, 2023: Sam is fired!

40

158

1K

SkalskiP

@skalskip92

4 months

YOLOv9 is out looks like a new SOTA real-time object detector I'm already working on a custom training tutorial

AK

@_akhaliq

4 months

YOLOv9 Learning What You Want to Learn Using Programmable Gradient Information Today's deep learning methods focus on how to design the most appropriate objective functions so that the prediction results of the model can be closest to the ground truth. Meanwhile, an appropriate

9

163

794

24

164

1K

SkalskiP

@skalskip92

3 months

manual data labeling is (almost) dead 1,500,000 images auto-annotated within 2 weeks of release. now, we also support automatic segmentation labeling. ↓ read more about open-source models that power this feature

51

136

1K

SkalskiP

@skalskip92

2 months

I need to take a break from football AI for a while. I plan to experiment with PaliGamma, Google's new open-source VLM, over the next few days. but don't worry, I'll be back. In the meantime, the football AI code is slowly making its way to this repo.

38

124

1K

SkalskiP

@skalskip92

4 months

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more

13

157

1K

SkalskiP

@skalskip92

11 months

supervision-0.13.0 is out! Now you can effortlessly count crops in the fields with a single drone flyby. GitHub repository:

11

153

1K

SkalskiP

@skalskip92

2 months

taking my football/soccer AI to the next level - image embeddings - dimension reduction - player clustering - awesome visualizations code: (code migration in progress...) ↓ read more

33

92

978

SkalskiP

@skalskip92

6 months

what stops you from using supervision today? link:

24

107

935

SkalskiP

@skalskip92

7 months

looking for OpenAI-4V alternatives? - LLaVA - BakLLaVA - CogVLM - Fuyu-8B - Qwen-VL I am working on a short blog post discussing some GPT-4V alternatives. It will probably come out today. links all resources:

SkalskiP

@skalskip92

7 months

What OpenAI-4V alternatives would you recommend? - LLaVA - BakLLaVA

45

44

488

43

154

927

SkalskiP

@skalskip92

8 months

Automated @NBA match commentary using @OpenAI vision and TTS (with code!) Everyone is bragging about projects that generate automatic video commentary, but no one is showing the code. I did it while waiting for the plane. code:

43

144

912

SkalskiP

@skalskip92

4 months

manual data labeling is almost dead define prompts, tweak the confidence threshold, and make manual adjustments if necessary. this feature is now available to all users, even on free accounts. read more:

12

125

917

SkalskiP

@skalskip92

9 days

Florence-2 is finally out! 1 model; 10+ computer vision tasks! ↓ key takeaways are listed below. see my blog post for details. link:

23

123

889

SkalskiP

@skalskip92

18 days

I spent most of today preparing for CVPR 2024 "Matching Anything by Segmenting Anything" particularly caught my attention. Here are the fast open-vocabulary tracking examples (MASA + YOLO-World). link: ↓ read more

7

122

877

SkalskiP

@skalskip92

5 months

how to calculate the TIME objects spend IN THE ZONE? - that's the topic of my next tutorial. here's a short (and a bit creepy) demo I built a few months ago. do you have ideas for a less creepy use case for this tech? github repository:

56

127

859

SkalskiP

@skalskip92

24 days

supervision 0.21.0 is launching tomorrow this update includes VertexLabelAnnotator, allowing you to annotate skeleton vertices with custom text and color link:

15

131

858

SkalskiP

@skalskip92

4 months

taking traffic analysis to the next level with supervision-0.19.0 speed estimation + 3d roead visualization link: ↓ read more

12

109

860

SkalskiP

@skalskip92

7 months

analyzing store traffic to find the most frequently visited areas super demo created by @Hine__Po - member of Supervision community link to repo if you want to build something over the weekend:

13

146

817

SkalskiP

@skalskip92

4 months

The YOLO-World YouTube tutorial is out! please, let us know what you think! - model architecture - processing images and video in Colab - prompt engineering and detection refinement - pros and cons of the model watch here: ↓ more resources

12

136

803

SkalskiP

@skalskip92

3 months

now you can run real-time object detection on multiple streams with 10 lines of code link: ↓ code snippet

13

141

789

SkalskiP

@skalskip92

4 months

YOLOv9 tutorial: train model on custom dataset - running inference with pre-trained COCO weights - fine-tuning the model on a custom dataset - model evaluation - model deployment sorry it took me so long; hope you like it

15

100

752

SkalskiP

@skalskip92

2 months

it took us a while, but the supervision-0.20.0 release will finally add support for key points. what are your thoughts on annotators? so far, we only have EdgeAnnotator and VertexAnnotator. supervision repo:

21

96

748

SkalskiP

@skalskip92

9 months

supervision-0.15.0 is out! This time, we bring highly customizable annotators. We added eight annotators - box, mask, ellipse, label, circle, corner, trace, and blur. But the best part is... you can freely mix them! GitHub repository:

9

126

737

SkalskiP

@skalskip92

1 month

YOLO is the craziest model family. Each version is created by a different organization. "Compared with YOLOv9-C, YOLOv10-B has 46% less latency and 25% fewer parameters for the same performance." I'll try to test it today. ↓ links

14

82

746

SkalskiP

@skalskip92

5 months

improving object counting logic today I solved an interesting bug that has existed in my library for a loooooong time repository: ↓ WARNING: lots of math in the thread below

7

80

739

SkalskiP

@skalskip92

9 months

Easily one of the most exciting projects built with Supervision! Our community member Vriza Wahyu Saputra built this fantastic ball juggling counting demo using the moving LineZone available in our API.

12

95

717

SkalskiP

@skalskip92

8 months

Am I the last person who didn't know about OpenAI Cookbook? link:

23

89

705

SkalskiP

@skalskip92

3 months

support for pose estimation and key point detection soon in the supervision you can expect connectors for the most popular models and the first annotators in the next supervision release can't wait to build demos like this with supervision

14

83

705

SkalskiP

@skalskip92

5 months

parking occupancy analysis calculation of percentage occupancy in individual parking zones all this was done with supervision: btw, @UenoLeo is cooking a blog post covering this project, so stay tuned! ↓ read more

13

97

703

SkalskiP

@skalskip92

3 months

I love watching other people build cool demos with the supervision library; traffic analysis examples built by Anant Jaiswal - object tracking - zone counting - heat-map analysis link:

4

94

704

SkalskiP

@skalskip92

4 months

smart self-service checkout powered by YOLOv9 the value of the basket is updated live based on its changing content; what else should I add? demo build with supervision:

14

90

704

SkalskiP

@skalskip92

8 months

What papers should I read to expand my knowledge of Transformers? Please send links in the comments and write why this paper is worth reading. Thanks for your help!

32

102

685

SkalskiP

@skalskip92

3 months

new YouTube tutorial: compute dwell time using computer vision in live streams (seems easy, yet tricky) - static file vs stream processing - preventing growing latency and frame buffer overflow - efficient stream processing full tutorial: ↓ read more

6

78

681

SkalskiP

@skalskip92

6 months

speed estimation tutorial is finally out! - object detection -multi-object tracking - filtering detections with polygon zone - perspective transformation and speed estimation link: below are some interesting visualizations I created for this video ↓

13

112

673

SkalskiP

@skalskip92

5 months

Qwen-VL-Plus is SACARY good! (better than GPT-4V) here it is casually solving Recaptcha! - You don't have to give any additional instructions other than 'Solve it.' - It can even mark the exact position of the objects it is looking for. ↓ it can do so much more

24

103

678

SkalskiP

@skalskip92

7 months

Sports Analytics with GPT-4 Vision I wondered whether GPT-4V had the capability to automatically separate players into teams based on the color of their uniforms. It took me a ridiculously long time to create this image, but in the meantime, I learned a lot about GPT-4V.

SkalskiP

@skalskip92

11 months

supervision-0.13.0 is out! We added ByteTrack support! Now you can easily plug in any object detector and use it for tracking. GitHub repository:

46

311

2K

20

89

669

SkalskiP

@skalskip92

11 months

- Object detection over HTTP? - Easy! We just open-sourced our inference server under Apache 2.0 Left terminal: @roboflow inference Right terminal: video client

6

80

662

SkalskiP

@skalskip92

10 months

The traffic analysis project is done! The YouTube tutorial will be out tomorrow. Stay tuned! Wait till flow counters appear around 0:06. Github repo:

17

100

651

SkalskiP

@skalskip92

8 months

SAM + MetaCLIP + ProPainter produce masks: remove object: I'm working on combo space!

7

102

616

SkalskiP

@skalskip92

1 month

I'm experimenting with PaliGemma tonight a single open-source model allowing you to: - detect car (detection) - answer questions about its color and brand (VQA) - read license plate number (OCR) all that on a single consumer-grade GPU is there any other model that can do it?

25

81

631

SkalskiP

@skalskip92

5 months

it blows my mind to see things that are created using my code

14

26

619

SkalskiP

@skalskip92

5 months

It took me ONE HOUR to craft this demo using supervision-0.18.0 - Three new annotators: PercentageBar, RoundedBox, and OrientedBox - Enhanced LineZone feature for improved counting - OBB (oriented bounding boxes) integration ↓ read more repo:

13

94

609

SkalskiP

@skalskip92

4 months

YOLO-World + EfficientSAM + StableDiffusion for language-guided inpainting I was inspired yesterday by the work of @MrDravcan (see attached), and I decided to try to replicate it. SPOILER ALERT: it didn't quite work out for me. ↓ read more

17

96

611

SkalskiP

@skalskip92

3 months

awesome example of using Supervision for the detection, annotation, and counting of coffee seedlings kudos to community member Eric Kimwatan supervision repo: ↓ youtube tutorial and colab

8

87

598

SkalskiP

@skalskip92

3 months

time-in-zone (dwell time) tutorial is coming this is the third time I'm trying to make this video; hopefully, the last one I finally have a good use case - waiting time for service. here is the first iteration. what do you think? link:

11

61

600

SkalskiP

@skalskip92

2 months

always triple-check the correctness of your datasets and data augmentations. today, I found two separate errors that ruined my model training. but finally, we are on the right track ↓ here's where I messed up

12

38

599

SkalskiP

@skalskip92

3 months

detecting small objects is hard I spent some time today writing a short how-to guide on using supervision (in combination with the most popular CV libraries) to detect small objects. btw is that a good idea for a video tutorial? link: ↓ read more

18

59

586

SkalskiP

@skalskip92

5 months

supervision-0.18.0 is almost here! we had planned to release it tomorrow, but we're still putting the finishing touches on the OBB (oriented bounding box) support repository:

6

67

583

SkalskiP

@skalskip92

7 months

Manually annotate ONE image and let GPT-4V annotate ALL of them. 1. generate boxes for all images with GroundingDINO 2. provide categories for the reference image 3. prompt GPT-4V to map generated boxes to reference categories

8

86

576

SkalskiP

@skalskip92

10 months

I'm working on a new YouTube tutorial... It's going to be sick! Here is v1 of my custom vehicle detector.

19

61

569

SkalskiP

@skalskip92

4 months

I'm experimenting with a new annotator that zooms in on small detections do you think it is something useful? or am I just wasting my time here? more cool annotators:

40

56

559

SkalskiP

@skalskip92

7 months

me: Find dog. gpt-4 vision: for the past few days I have been working on a library for advanced prompting of LMMs here it is:

16

77

553

SkalskiP

@skalskip92

4 months

processing documents with Claude 3 - Good OCR capabilities - Process up to 20 images with a single API call - API seems slow and a bit unstable; expect a lot of variance in call execution time - ~2x cheaper than GPT4-V (please check my math) ↓ read more

10

47

543

SkalskiP

@skalskip92

9 months

Working on a new tutorial - time in the zone. Detection, tracking, and zones are ready. Time to add timers. GitHub repository:

9

96

536

SkalskiP

@skalskip92

3 months

time analysis with computer vision - blurring faces - detection and tracking - smoothing detections - filtering detections by zone - calculating time let me know if you want me to explain anything else. ;) code: ↓ read more

8

58

523

SkalskiP

@skalskip92

6 months

finally had a little bit of time to work on my upcoming vehicle speed estimation tutorial any improvement ideas? the demo was built with the supervision code will soon land on GitHub:

26

77

496

SkalskiP

@skalskip92

9 months

Is that demo too creepy? Ignore that one lady sitting in the zona since the beginning is undetected. I am still trying to figure out why... But zone timers work! GitHub repository:

39

80

513

SkalskiP

@skalskip92

4 months

🔴 stream: YOLO-World Q&A + coding in less than 15 minutes, I start my first YT stream; I'll be talking about YOLO-World and answering your questions that you left under my last YT video stop by to say hello link: ↓ some of the topics we will cover

7

73

512

SkalskiP

@skalskip92

1 year

Two months ago, I created a @github repository where I gathered links to the best free AI courses. 🔥 I started with five links, and now there are almost 20. 🚀 The entire repository already has 1200+ ⭐ ⮑ 🔗 GitHub repository: ↓🧵some of the courses

8

152

495

SkalskiP

@skalskip92

1 month

YOLOv10 is fast and light but is NOT the best choice for detecting small objects in the distance. - YOLOv8 - top-right - YOLOv9 - bottom-left - YOLOv10 - bottom-right YOLOv10 performs worse.

8

57

511

SkalskiP

@skalskip92

17 days

the moment @karpathy knows your open-source project exist; now I can die in peace 🤯

SkalskiP

@skalskip92

17 days

supervision - a computer vision library I created - just crossed 15,000 stars on GitHub! BBBRRRRRR! link:

50

598

6K

16

14

508

SkalskiP

@skalskip92

3 months

OpenAI, xAI, and... Supervision top 5 on GitHub trending!

SkalskiP

@skalskip92

3 months

supervision, the open-source library I created a year ago, has crossed 10,000 stars on GitHub this weekend! thank you to everyone who helped me build this project! it took us 2,000+ commits, 500+ PRs and 50+ contributors to do it. repository:

21

313

2K

19

42

484

SkalskiP

@skalskip92

9 days

Thursday afternoon posters session #CVPR2024 YOLO-World: Real-Time Open-Vocabulary Object Detection [223] TL;DR: YOLO-World enhances the YOLO detector series with open-vocabulary detection capabilities, overcoming limitations of predefined object categories. ↓

7

95

567

SkalskiP

@skalskip92

7 months

What OpenAI-4V alternatives would you recommend? - LLaVA - BakLLaVA

45

44

488

SkalskiP

@skalskip92

7 months

supervision-0.17.0 release is just around the corner - plug in your favorite detection/segmentation model - compose the perfect visualization github:

9

92

487

SkalskiP

@skalskip92

10 months

Traffic Analysis Tutorial is out! I'm sorry for the delay. I didn't expect it to be 23 minutes long. Please let me know what you think. YouTube video:

13

101

488

SkalskiP

@skalskip92

7 months

using GPT-4V to split players into teams blending detections with the same tracker ID allows you to significantly reduce the number of GPT-4V API calls when you process video 1 call / 25 frames kudos to @ikuma_uchida18 for coming up with this strategy read more, it's cool ↓

SkalskiP

@skalskip92

7 months

Sports Analytics with GPT-4 Vision I wondered whether GPT-4V had the capability to automatically separate players into teams based on the color of their uniforms. It took me a ridiculously long time to create this image, but in the meantime, I learned a lot about GPT-4V.

20

89

669

9

79

470

SkalskiP

@skalskip92

8 months

The second day of work on my SAM + MetaCLIP + ProPainter HF Space - Automated object masking [done] - Automated inpainting using ProPainter [in progress]

13

67

464

SkalskiP

@skalskip92

13 days

I know my football AI isn't quite there yet, but this motivates me to add some advanced features after I get back from CVPR 2024. I'll keep you guys posted! link:

8

26

473

SkalskiP

@skalskip92

8 months

I just added the polygon annotator to the supervision package you can now use masks or polygons to visualize the result of the instance segmentation model polygon annotator will be available in supervision-0.17.0 code:

5

53

455

SkalskiP

@skalskip92

7 months

processing this one-second video exhausted my entire daily quota of 500 GPT-4V requests but if you were wondering, @OpenAI GPT-4V can automatically divide players into teams based on the color of their uniforms

SkalskiP

@skalskip92

7 months

Sports Analytics with GPT-4 Vision I wondered whether GPT-4V had the capability to automatically separate players into teams based on the color of their uniforms. It took me a ridiculously long time to create this image, but in the meantime, I learned a lot about GPT-4V.

20

89

669

26

62

448

SkalskiP

@skalskip92

5 months

defect detection with computer vision training and deploying manufacturing defect detector step-by-step guide blog post: ↓ read more

9

71

456

SkalskiP

@skalskip92

1 month

detecting small and distant objects is a major weakness of YOLOv10. here is the comparison of YOLOv8l at 640x640 and YOLOv10l at 640x640: - green: detected by YOLOv8 and YOLOv10 - red: detected only by YOLOv8 - blue: detected only by YOLOv10

SkalskiP

@skalskip92

1 month

YOLOv10 is fast and light but is NOT the best choice for detecting small objects in the distance. - YOLOv8 - top-right - YOLOv9 - bottom-left - YOLOv10 - bottom-right YOLOv10 performs worse.

8

57

511

9

55

448

SkalskiP

@skalskip92

2 months

estimating traffic density based on the live feed from NYC street cameras. you can find out in real-time which streets are congested. shoutout to @UenoLeo for creating this cool project!

7

50

446

SkalskiP

@skalskip92

8 months

Segment Anything (SAM) + MetaCLIP - unleashing the full power of @Meta open source! I'm having fun with @Gradio today!

Niels Rogge

@NielsRogge

8 months

CLIP by @OpenAI was revolutionary, but its data curation pipeline was never detailed nor open-sourced. @Meta has now released MetaCLIP, a fully open-source replication. Models are on the hub:

17

172

1K

10

73

437

SkalskiP

@skalskip92

11 days

live GPT-4o demo by @rown from OpenAI at #CVPR2024

21

49

435

SkalskiP

@skalskip92

4 months

YOLO (unofficial and incomplete) history who made what? while I wait for my first YOLOv9 model custom dataset fine-tuning to finish, I decided to share with you an incomplete YOLO history with links to papers and code YOLO (2016) Joseph Redmon et al. - paper:

4

60

424

SkalskiP

@skalskip92

15 days

obviously torch vision is a lot more important than supervision :) still it’s awesome feeling to see my tiny library overtaking this freaking giant on GitHub link:

8

27

427

SkalskiP

@skalskip92

4 months

zero-shot video object detection with YOLO-World as promised, I just updated my @huggingface ; have fun! space:

8

71

413

SkalskiP

@skalskip92

9 months

supervision-0.15.0 will be out tomorrow! This time we bring highly customizable annotators. Just plug in your model and we'll take care of the rest. GitHub repository:

4

62

412

SkalskiP

@skalskip92

8 months

Adding meaningful regions and labels significantly improves GPT-4V's reasoning capabilities.

18

68

403

SkalskiP

@skalskip92

8 months

the must-have resource for anyone who wants to experiment with and build on the @OpenAI Vision API code:

7

57

402

SkalskiP

@skalskip92

3 months

zone analysis is awesome; you can use it to calculate an object's precise position in space, determine its movement path, or measure its distance traveled. air traffic monitoring demo by @carlos_melo_py supervision repo: ↓ youtube tutorial and code

5

56

403

SkalskiP

@skalskip92

3 months

whenever I show zone analysis in my tutorials, people ask me how I designed the polygons I decided to spend a few hours and create for you a small tool you can fire up locally to draw zones code:

8

36

398