Data Science by ODS.ai 🦜

2022-07-24 08:05:50 ​​Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

While vision transformers demostrate high performance, they can't be deployed as efficiently as CNNs in realistic industrial deployment scenarios, e. g. TensorRT or CoreML.

The authors propose Next-ViT, which has a higher latency/accuracy trade-off than existing CNN and ViT models. They develop two new architecture blocks and a new paradigm to stack them. As a result, On TensorRT, Next-ViT surpasses ResNet by 5.4 mAP (from 40.4 to 45.8) on COCO detection and 8.2% mIoU (from 38.8% to 47.0%) on ADE20K segmentation. Also, it achieves comparable performance with CSWin, while the inference speed is accelerated by
3.6×. On CoreML, Next-ViT surpasses EfficientFormer by 4.6 mAP (from 42.6 to 47.2) on COCO detection and 3.5% mIoU (from 45.2% to 48.7%) on ADE20K segmentation under similar latency.

Paper: https://arxiv.org/abs/2207.05501

A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-next-vit

#deeplearning #cv #transformer #computervision Open / Comment

2022-07-23 15:22:01 Some stats to get the perspective of the development of #dalle

«Used 1000 prompts in Dalle over the last 2 days, about 9 hours each day. Of those, saved ~300. 50 I like enough to share w/ socials. 12 enough to rework for future projects. 3 were perfect, may mint someday. Curation is *1* step of AI art. I used to finish physicals in less time.»

Source: https://twitter.com/clairesilver12/status/1550709299797577729

#visualization #gan #generation #generatinveart #aiart #artgentips Open / Comment

2022-07-23 13:19:50 DALL·E Now Available in Beta #Dalle by #openai was released for public (though obviously moderated) access. Join waitlist to play around. Images are also available for commercial use. By default user can generate 460 images, further generations (or variations… Open / Comment

2022-07-22 14:40:20 ​​Big step after first DALL·E — DALL·E 2 In January 2021, OpenAI introduced DALL·E. One year later, their newest system, DALL·E 2, generates more realistic and accurate images with 4x greater resolution. The first DALL·E is a transformer model. It receives… Open / Comment

2022-07-20 13:24:22 A.W.E.S.O.M. O is an extensive list of interesting open source projects written in various languages.

#python #rust #js #php #golang #go #ts #kotlin #js #clojure #erlang #elixir #c #cpp #dart #ocaml #etc Open / Comment

2022-07-15 19:48:03 ​​the #dalle prompt book
first edition

free to download, it features 82 pages of artistic inspiration with over 300 examples of dalle2 images Open / Comment

2022-07-09 21:18:20 ​​No Language Left Behind
Scaling Human-Centered Machine Translation

No Language Left Behind (NLLB) is a first-of-its-kind, AI breakthrough project that open-sources models capable of delivering high-quality translations directly between any pair of 200+ languages — including low-resource languages like Asturian, Luganda, Urdu and more. It aims to help people communicate with anyone, anywhere, regardless of their language preferences.

To enable the community to leverage and build on top of NLLB, the lab open source all they evaluation benchmarks (FLORES-200, NLLB-MD, Toxicity-200), LID models and training code, LASER3 encoders, data mining code, MMT training and inference code and our final NLLB-200 models and their smaller distilled versions, for easier use and adoption by the research community.


Paper: https://research.facebook.com/publications/no-language-left-behind/
Blog: https://ai.facebook.com/blog/nllb-200-high-quality-machine-translation/
GitHub: https://github.com/facebookresearch/fairseq/tree/26d62ae8fbf3deccf01a138d704be1e5c346ca9a

#nlp #translations #dl #datasets Open / Comment

2022-07-08 21:16:26 Today mimesis has been designated as a critical project on PyPI.

It's ain't much, but I feel warm when I think about how many people use think I built.

Thank you everyone!

P.S If you don't know what the hell mimesis is, then go and check it out. Maybe you'll find it useful for you.

#mimesis #pypi #python Open / Comment

2022-07-02 10:45:54 In 15 minutes, start the last section of DataFestOnline 2022.

[language of presentations - Russian]

Mikhail Neretin - Topic management in Kafka
Evgeniy Sorokin - Human and ML => collaboration
Olga Filippova - Data drift & Concept drift: How to monitor ML models in production
Dmitry Beloborodov - Matrix factorizations with embeddings of variable dimension
Stanislav Yarkin - Summarization Is All You Need: summarization in RecSys
Artem Trofimov - MLOps by DS forces
Possible: Secret Speaker - MLEM: Version and deploy your ML models following Hitops principles

Start at 11:00 MSK (UTC+3)
There is an opportunity to ask a question to the speaker

Where?
Come to the session -> https://live.ods.ai/
Room: Last chance
Password: followthepinkparrot Open / Comment

2022-06-23 18:44:05 Yandex: An Open-source Yet another Language Model 100B

YaLM 100B is trained for 2 terabyte of text: dataset the Pile and web-pages, including not only Wikipedia, news articles, and books, but also Github and arxiv.org. Yandex has applied the generative neural networks YaLM in the recent Y1 search update. Now they are already helping to give answers to searches in Yandex and Alice.

Github: https://github.com/yandex/YaLM-100B

@ai_machinelearning_big_data Open / Comment