@__setitem__ Profile picture

Varun Kapoor

@__setitem__

Staff ML engineer at Kietzmann Lab, founder of non-profit @kapoorlabs

Joined October 2022
Similar User
Victoria Bosch photo

@__init_self

Dirk Gütlin photo

@DirkGutlin

Philip Sulewski photo

@PhilipSulewski

Daniel Anthes photo

@AnthesDaniel

Viviane Clay photo

@vkakerbeck

Rowan Sommers photo

@RowanSommers

Thirza Dado photo

@ThirzaDado

Mathis Pink photo

@MathisPink

Lu-Chun Yeh photo

@LuChunYeh

Johannes Roth photo

@andropar

Lenny van Dyck photo

@levandyck

Florian Mahner photo

@florianmahner

Laura Stalenhoef photo

@StalenhoefLaura

Maëlle Lerebourg photo

@MaelleLerebourg

Varun Kapoor Reposted

We are announcing that PyTorch will stop publishing Anaconda packages on PyTorch’s official anaconda channels. For more information, please refer to the following post on dev-discuss: dev-discuss.pytorch.org/t/pytorch-depr…


Varun Kapoor Reposted
_willfalcon's tweet image.

Varun Kapoor Reposted

The 'ResNet Strikes Back' paper is so good. We should try to create better (and simpler) training procedures more often. Our paper 'Simplifying neural network training under class imbalance' was an attempt to do it for imbalanced training. arxiv.org/abs/2312.02517

I released timm 1.0.8 last night. The recent MobileNet baseline weights are part of the release, check out my previous tweet. A small update w/ several new MobileNet-v4 anti-aliased and in12k models & weights in there. Additionally more flexibility for vit & swin image size...



Varun Kapoor Reposted

🐍🎧 Constraint Programming & Exploring Python's Built-in Functions What are discrete optimization problems? How do you solve them with constraint programming in Python? @cltrudeau is back bringing another batch of PyCoder's Weekly articles and projects. realpython.com/podcasts/rpp/2…

realpython's tweet image. 🐍🎧 Constraint Programming & Exploring Python's Built-in Functions

What are discrete optimization problems? How do you solve them with constraint programming in Python? @cltrudeau is back bringing another batch of PyCoder's Weekly articles and projects.

<a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/GADeJsWetB">realpython.com/podcasts/rpp/2…</a>

Varun Kapoor Reposted

As you read this, both your phone’s software and your brain’s neural networks are operating in predictable ways even though the electrons’ trajectories and neuronal firing patterns are never exactly the same. Scientists are working out how this is possible.quantamagazine.org/the-new-math-o…


Awesome feeling to exercise brain muscles in tandem with other muscles. Todays topic of choice: deep gaze I

__setitem__'s tweet image. Awesome feeling to exercise brain muscles in tandem with other muscles. Todays topic of choice: deep gaze I
__setitem__'s tweet image. Awesome feeling to exercise brain muscles in tandem with other muscles. Todays topic of choice: deep gaze I
__setitem__'s tweet image. Awesome feeling to exercise brain muscles in tandem with other muscles. Todays topic of choice: deep gaze I
__setitem__'s tweet image. Awesome feeling to exercise brain muscles in tandem with other muscles. Todays topic of choice: deep gaze I

Varun Kapoor Reposted

Excited to announce the second iteration of NEAT (Neuro-AI-Talks), which will take place September 2nd-3rd 2024 in Osnabrück. kietzmannlab.org/neat2024 Never heard of it? Let me tell you what this is about 🧵

TimKietzmann's tweet image. Excited to announce the second iteration of NEAT (Neuro-AI-Talks), which will take place  September 2nd-3rd 2024 in Osnabrück.

<a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/TL3XtuHmlC">kietzmannlab.org/neat2024</a>

Never heard of it? Let me tell you what this is about 🧵

Varun Kapoor Reposted

I swear if i train a model I'm just going to use @pytorch and @LightningAI ... every other lib is so unserious


Varun Kapoor Reposted

🤝 Solve tasks and develop AI solutions with the help of automated workflows, where humans and AI models work together.


Varun Kapoor Reposted

aMUSEd's small size opens up doors to local hacking. Just chugged my local M2 and it went like a breeze with a batch size of 4 and 12 steps. Check out aMUSEd here 👉 huggingface.co/blog/amused


Varun Kapoor Reposted

KerasCV now includes a Segment Anything implementation, which enables you to do image segmentation using only "prompt points". No training data needed. With the JAX backend, it runs ~5x faster on GPU than the original PyTorch implementation. Told you JAX was fast. Guide:…


Varun Kapoor Reposted

This is one of the hidden secrets of scalable research labs: creating template experimental codebases that allow fast testing of wild research ideas. You need your experiment, data, compute, and model abstractions just right 1/

it also follows that the returns to making simple codebases to test research ideas must be really high and also that the returns to making ai engineering tools are enormously high



Varun Kapoor Reposted

#NEAT2023 was a blast, thanks to everyone joining us in Osnabrück for a day of interaction, collaboration and neuroAI

TimKietzmann's tweet image. #NEAT2023 was a blast, thanks to everyone joining us in Osnabrück for a day of interaction, collaboration and neuroAI

Varun Kapoor Reposted

Inside the Matrix: Use 3D to visualize matrix multiplication expressions, attention heads with real weights, and more. ⚡ Read our latest post on visualizing matrix multiplication, attention and beyond: hubs.ly/Q0230BWD0


Varun Kapoor Reposted

NEW PAPER 🧵: Deep neural networks are complicated, but looking inside them ought to be simple. In this paper we introduce TorchLens, a package for extracting all activations and metadata from any #PyTorch model, and visualizing its structure, in as little as one line of code. 1/

johnmark_taylor's tweet image. NEW PAPER 🧵: Deep neural networks are complicated, but looking inside them ought to be simple. In this paper we introduce TorchLens, a package for extracting all activations and metadata from any #PyTorch model, and visualizing its structure, in as little as one line of code. 1/

Varun Kapoor Reposted

As some of you have asked, here is a link to my CCN keynote from this year. Main topic: how we use ANNs as a language to describe, implement, and test theories of brain computations. #neuroconnectionism youtube.com/watch?v=pwFh_b…


Varun Kapoor Reposted

Folks using @weights_biases with @pytorchlightnin using our WandbLogger, faces the misalignment issue. The `global_step` is not the same as wandb's internal `step`. This makes comparing a training run with a training+validation run. The solution is simple. Check out this video:


Loading...

Something went wrong.


Something went wrong.