Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We've added 15 new Computer Vision problems. revise your concepts by coding them out: > max pooling > image rotation > gaussian blur kernel > sobel edge detection > image histogram > 2D convolution > IoU > Non-maximum supression etc

TensorTonic's profile picture

TensorTonic

9,898 subscribers

35,683 Aufrufe • vor 6 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Most awaited Optimization techniques in Machine Learning module is out! We've covered the fundamentals of - > SGD variants > Convex vs Non-Convex > Momentum & Nesterov acc. > Adam, RMSprop > Loss landscapes > Regularization > Batch Norm > Newton's method & lagrange
0:28

Most awaited Optimization techniques in Machine Learning module is out! We've covered the fundamentals of - > SGD variants > Convex vs Non-Convex > Momentum & Nesterov acc. > Adam, RMSprop > Loss landscapes > Regularization > Batch Norm > Newton's method & lagrange

TensorTonic

44,023 Aufrufe • vor 8 Monaten

Our final module is out! We've covered the fundamentals of Information theory. topics include - > shannon entropy > KL divergence > information gain (decision trees) > mutual information > cross entropy loss > GANs training > Jensen-Shannon Divergence > Perplexity
0:23

Our final module is out! We've covered the fundamentals of Information theory. topics include - > shannon entropy > KL divergence > information gain (decision trees) > mutual information > cross entropy loss > GANs training > Jensen-Shannon Divergence > Perplexity

TensorTonic

54,330 Aufrufe • vor 8 Monaten

we have released more blogs today on calculus fundamentals for machine learning and their interactive simulations. some of them includes - > backprop and gradient descents > local minima/saddle points > vector fields > taylor series > jacobian and hessian > partial derivatives
0:35

we have released more blogs today on calculus fundamentals for machine learning and their interactive simulations. some of them includes - > backprop and gradient descents > local minima/saddle points > vector fields > taylor series > jacobian and hessian > partial derivatives

TensorTonic

66,968 Aufrufe • vor 8 Monaten

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.
0:21

New open source image model called Mage-Flow by Microsoft. > Supports image generation and editing. > Lightweight 4B model with 4-step turbo variants. > Free and open-source, MIT license.

⚡AI Search⚡

14,424 Aufrufe • vor 1 Monat

Module for Graph Theory in Machine Learning is live! this includes fundamentals to - > computational graph (how pytorch works) > Graph representation > GNNs > Message Passing in GNNs > Spectral graph theory > random walks & markov chains
0:22

Module for Graph Theory in Machine Learning is live! this includes fundamentals to - > computational graph (how pytorch works) > Graph representation > GNNs > Message Passing in GNNs > Spectral graph theory > random walks & markov chains

TensorTonic

22,040 Aufrufe • vor 8 Monaten

Don't miss out 🎤 YouTube star Max Fosh brings new show Loophole on tour. Grab your tickets 🎟️ >> Max Fosh
0:59

Don't miss out 🎤 YouTube star Max Fosh brings new show Loophole on tour. Grab your tickets 🎟️ >> Max Fosh

ticketmasteruk

289,035 Aufrufe • vor 2 Jahren

> Upload your ad comments into ChatGPT > Rank objections by most popular > Get Claude to write a Facebook ad script addressing the objection > Make a comment response ad out of it and thank me later We've made 4 of these so far and 3 have worked
1:04

> Upload your ad comments into ChatGPT > Rank objections by most popular > Get Claude to write a Facebook ad script addressing the objection > Make a comment response ad out of it and thank me later We've made 4 of these so far and 3 have worked

Alex Cooper

11,567 Aufrufe • vor 1 Jahr

Nitin Gadkari told ; we will spend ₹ 65000 Crore & make Delhi pollution free by end of 2025 His past promises are : > Making all Indian roads like USA > Flying Buses > Ethanol usage in Cars etc No need to say, non of them are fulfilled 🤗
3:19

Nitin Gadkari told ; we will spend ₹ 65000 Crore & make Delhi pollution free by end of 2025 His past promises are : > Making all Indian roads like USA > Flying Buses > Ethanol usage in Cars etc No need to say, non of them are fulfilled 🤗

Veena Jain

257,290 Aufrufe • vor 1 Jahr

Beep beep, new Bret Weinstein medical advice has come in. -> Getting measles is good for you -> Measles protects you from other diseases -> Your child won't be in danger of getting harmed by measles as long as you protect them from WiFi radiation and offgassing
1:53

Beep beep, new Bret Weinstein medical advice has come in. -> Getting measles is good for you -> Measles protects you from other diseases -> Your child won't be in danger of getting harmed by measles as long as you protect them from WiFi radiation and offgassing

bad_stats 🕜💵🖨️🕣

36,528 Aufrufe • vor 5 Monaten

Galeria 1 is now available – an image viewer for React (+ Native) → New Architecture Support → Stable web support → Bring-your-own-image component Automatic support for: solito/image, next/image, expo-image, react-native-fast-image, web <img />
0:41

Galeria 1 is now available – an image viewer for React (+ Native) → New Architecture Support → Stable web support → Bring-your-own-image component Automatic support for: solito/image, next/image, expo-image, react-native-fast-image, web <img />

Fernando Rojo

27,366 Aufrufe • vor 1 Jahr

Check out our new paper that turns a (single image) => (interactive dynamic scene)! I’ve had so much fun playing around with this demo. Try it out yourself on the website:
0:22

Check out our new paper that turns a (single image) => (interactive dynamic scene)! I’ve had so much fun playing around with this demo. Try it out yourself on the website:

Aleksander Holynski

301,765 Aufrufe • vor 3 Jahren

Turn images into decentralized videos with Eternal AI Upload an image and tweet: Eternal AI create video <your prompt> It'll reply with a short video using your image, powered by Wan2.1 by Wan, stored on Filecoin, and verifiable onchain with Base.
0:25

Turn images into decentralized videos with Eternal AI Upload an image and tweet: Eternal AI create video <your prompt> It'll reply with a short video using your image, powered by Wan2.1 by Wan, stored on Filecoin, and verifiable onchain with Base.

Eternal AI

44,370 Aufrufe • vor 1 Jahr

CAT3D + time => CAT4D! 🐈 Check out our latest work on turning text/image(s)/video into dynamic 3D models that one can explore in real time, led by brilliant Rundi Wu!
0:36

CAT3D + time => CAT4D! 🐈 Check out our latest work on turning text/image(s)/video into dynamic 3D models that one can explore in real time, led by brilliant Rundi Wu!

Ruiqi Gao

21,908 Aufrufe • vor 1 Jahr

Quick test of Fable 5.1 for 3D model generation - 3DAIStudio MCP for GPT Image 2 -> Tripo P2 - Blender via Computer Use to sort out normals, merge by distance & material grouping (via L for linked face selection) - Adobe Substance 3D Painter via Computer Use Pretty good!
0:59

Quick test of Fable 5.1 for 3D model generation - 3DAIStudio MCP for GPT Image 2 -> Tripo P2 - Blender via Computer Use to sort out normals, merge by distance & material grouping (via L for linked face selection) - Adobe Substance 3D Painter via Computer Use Pretty good!

Matt

13,196 Aufrufe • vor 8 Tagen

I created a web app for teaching computer vision basics, allowing users to upload an image or video stream and instantly view it as a numerical pixel matrix, with options to display values in RGB, Hex, or Grayscale formats. It features predefined convolution kernels applied in real-time: - Sobel operator for edge detection (computes gradients to highlight boundaries) - Gaussian Blur: averages neighboring pixels with weights to reduce noise - Sharpen: boosts local contrast to enhance details This setup clearly visualizes how images are represented as matrices or tensors, how convolution slides kernels across pixels, and how operations like gradient computation, blurring, or sharpening modify the data step-by-step. I plan to use demos like this in my upcoming computer vision course to build intuition for fundamental image processing concepts, OpenCV filters, and CNN building blocks (e.g., why kernels extract features).
0:25

I created a web app for teaching computer vision basics, allowing users to upload an image or video stream and instantly view it as a numerical pixel matrix, with options to display values in RGB, Hex, or Grayscale formats. It features predefined convolution kernels applied in real-time: - Sobel operator for edge detection (computes gradients to highlight boundaries) - Gaussian Blur: averages neighboring pixels with weights to reduce noise - Sharpen: boosts local contrast to enhance details This setup clearly visualizes how images are represented as matrices or tensors, how convolution slides kernels across pixels, and how operations like gradient computation, blurring, or sharpening modify the data step-by-step. I plan to use demos like this in my upcoming computer vision course to build intuition for fundamental image processing concepts, OpenCV filters, and CNN building blocks (e.g., why kernels extract features).

Marco Franzon

270,367 Aufrufe • vor 8 Monaten

If you've made >100 images with Midjourney you can now help us alpha-test image creation on our website. We've also added a 'rooms' feature where you can create in real-time with people around the world. Give it a shot and let us know what you think!
4:46

If you've made >100 images with Midjourney you can now help us alpha-test image creation on our website. We've also added a 'rooms' feature where you can create in real-time with people around the world. Give it a shot and let us know what you think!

Midjourney

109,940 Aufrufe • vor 2 Jahren

Introducing Diagnose and Debug. Give your agent first-party backend context: health metrics, logs, errors, database checks, and more. Your coding agent catches backend issues now, then fixes them by working with your dedicated InsForge debugging agent. Agent <> Agent.
1:50

Introducing Diagnose and Debug. Give your agent first-party backend context: health metrics, logs, errors, database checks, and more. Your coding agent catches backend issues now, then fixes them by working with your dedicated InsForge debugging agent. Agent <> Agent.

InsForge

53,074 Aufrufe • vor 3 Monaten

My brother and I just launched an app! Nutrify, a Pokédex for food 📸 -> 🍍 Nutrify uses computer vision to identify different foods and display information about them. Try it on the iOS App Store for free today! Check out the launch video too! (more links below)
5:04

My brother and I just launched an app! Nutrify, a Pokédex for food 📸 -> 🍍 Nutrify uses computer vision to identify different foods and display information about them. Try it on the iOS App Store for free today! Check out the launch video too! (more links below)

Daniel Bourke

19,846 Aufrufe • vor 2 Jahren

The mysterious #Toyota GT Concept. Destined to be the new flagship sports road car for Toyota, followed by the brand new GT racing concept. These two took on the #FOS Hill together creating a harmonious sound for the first time ever in front of crowds, piloted by three-time #LeMans winner Kazui Nakajima. We don't have much information on them yet but we are very much looking forward to finding out more in the future... Are you following along on our livestream? ToyotaUK
2:34

The mysterious #Toyota GT Concept. Destined to be the new flagship sports road car for Toyota, followed by the brand new GT racing concept. These two took on the #FOS Hill together creating a harmonious sound for the first time ever in front of crowds, piloted by three-time #LeMans winner Kazui Nakajima. We don't have much information on them yet but we are very much looking forward to finding out more in the future... Are you following along on our livestream? ToyotaUK

Goodwood FOS

525,282 Aufrufe • vor 1 Jahr

Introducing SWE-grep and SWE-grep-mini: Cognition’s model family for fast agentic search at >2,800 TPS. Surface the right files to your coding agent 20x faster. Now rolling out gradually to Windsurf users via the Fast Context subagent – or try it in our new playground!
0:28

Introducing SWE-grep and SWE-grep-mini: Cognition’s model family for fast agentic search at >2,800 TPS. Surface the right files to your coding agent 20x faster. Now rolling out gradually to Windsurf users via the Fast Context subagent – or try it in our new playground!

Cognition

664,561 Aufrufe • vor 10 Monaten