I created gpt-scraper to automate data extraction from sites with unique structures — just describe what data you need, and the AI-powered library writes the scraper code for you. With the new o1-mini model, it’s faster and more accurate than ever! https://t.co/8F6oEf8TKD

My first contribution to open-source protein design: a new way to combine ProteinMPNN and AlphaFold for designing sequences for a given structure https://t.co/XwQ7IsrXjO More context and info below 👇

The new version of our engine for Stable Diffusion optimized to CPU is ready. Now it supports Image-To-Image and Inpainting too. Also, we release the initial version of pretty GUI. Join to the future of media art here: https://t.co/bQMSD975PO… #art #deeplearning

We published our early results to run state-of-the-art Text-To-Image models on consumer CPU. You can found project here: https://t.co/bQMSD975PO #syntheticmedai #stablediffusion #ai #openvino

I uploaded a simple sample using MobileStyleGAN on iOS to GitHub. https://t.co/EKu5WqOblh The Converted CoreML model have been uploaded to CoreML-Models. https://t.co/75Fxf3POnB

Our new library for text-driven bounding box analysis was published. Also we provide examples to integrate it with popular object detector like YOLOV5 and MaskRCNN. https://t.co/ZSlOv0LpxU #OpenSource #Python #DeepLearning

Our new tiny zero-shot text-driven object detector named ClipRCNN was released: https://t.co/sJrMkePt3y #opensource #deeplearning #computervision

Our new library to make CLIP guided loss for Text-To-Image generation was published on github: https://t.co/JcvUNg8VYv #opensource #python #deeplearning

Our new library to make differentiable Haar Wavelets Transform was published on github: https://t.co/hdR991bW1X #OpenSource #Python #DeepLearning #PyTorch

Just a one-weekend project 🤗 We propose a new architecture of theDecoder network (based on VQVAE's decoder) for DALL-E that allows to generate images 512x512 instead of 256x256 as in baseline DALL-E model: https://t.co/4czqgLyUhM #deeplearning #dalle #gans #opensource

The new version of our library for fast image generation of people who do not exist was released. x2 Better quality of generated images is here (= python library: https://t.co/iGJpa4pO7T training tool: https://t.co/bwRH2jSZtZ demo video: https://t.co/jXKLLsNd01

Now, high-resolution style-based generative models run on mobile devices! On-device demo of our MobileStyleGAN is here: https://t.co/VXTnV7AaWB Follow the project: https://t.co/bwRH2jSZtZ

Today, my new article was published: MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis Paper: https://t.co/LDClLuQfpJ Code: https://t.co/bwRH2jSZtZ Python library: https://t.co/iGJpa4pO7T Sample videos:

The near future of live #MMA (and sports) broadcasting is with #ComputerVision and #AI #UFC #DanaWhite

Some time ago, for internal use in my projects, I created a simple library for the evaluation of mAP for Object Detection algorithms that can be easily integrated into different pipelines. And now I published it on github. Enjoy using!

My colleagues released Intel's public online server for CVAT: https://t.co/rQZyEey7ij. This server provides an online labeling tool for your computer vision datasets. We hope that it will be helpful in your great projects.

@randal_olson @MaloyanNarek @kaggle 1. We, as a team, would like to apologize to @myPetFinder @kaggle and the DS community for all the wrongdoings. I would also like to apologize to @h2oai and all the Kaggle competitors for putting their reputation at risk.

OpenVINO neural networks compression framework was release (PyTorch based). Key features: 1) Trainable quantization for weights/activations 2) Sparsification based on magnitude or L0 regularization 3) Static graph parsing for Pytorch. github:

After years in academia, @Kaggle Grandmaster @viglovikov transitioned to the industry where the impact of the #selfdriving challenge caught his attention. Hear in his own words how he went from publishing papers to developing self-driving cars:

I'm a big fan of the DVC (Data Version Control) peeps. @shcheklein, @rkuprieiev, and co. are helping data scientists version control their models and experiments with an open source framework. Check it out at