When will @ChatGPT create great cartoons?
MULTIMODAL AI
-
Researchers Release MiniGPT-4 Open Source Multimodal AI Model
By
–
Nice! A “Mini” open source AI multimodal Transformer model. https://
analyticsindiamag.com/researchers-re
lease-multimodal-minigpt-4-before-openai/
… cc @pierrepinna @tdinh_me -
Visual Prompting: Extending Text Prompting to Computer Vision
By
–
Join me Tuesday to discuss Visual Prompting! Text prompting has revolutionized NLP: Traditional AI: Label -> Train -> Predict
Prompt based AI: Prompt -> Predict I’ll share early thoughts on taking this from text to vision w/Visual Prompting. RSVP here: https://
landing.ai/visual-prompti
ng
… -
AI Technology Helps Locate Lost Glasses Automatically
By
–
t'aura plus a chercher où t'a paumé tes lunettes aussi
-
Automatic mask generation pipeline released by Hugging Face
By
–
Automatic mask generation pipeline! With one line of code predict automatically the segmentation masks of a given image (similar as the examples above) Check out the example notebook: https://
github.com/huggingface/no
tebooks/blob/main/examples/automatic_mask_generation.ipynb
… -
SAM Model Documentation and Features Overview
By
–
You can first read more about the model, and learn how to use it on our documentation page: https://
huggingface.co/docs/transform
ers/main/en/model_doc/sam
…
Let's check all the features we support below! -
SAM Meta Segmentation Model Now Available in Transformers
By
–
SAM, the groundbreaking segmentation model from @Meta is now in available in Transformers!
What does this mean? 1. One line of code to load it, one line to run it
2. Efficient batching support to generate multiple masks
3. pipeline support for easier usage More details: -
Transformer Models Enable Learning Across Languages and Data Types
By
–
You can use it for language, you can even use it for images, you can use it for proteins, chemicals, videos, and so. There are many languages you can learn using the transformer model", explained Jensen.
-
Real Image-Based Generation Advances AI Creative Capabilities
By
–
il l'a fait à partir de vraies images par contre 😉
-
Vector Matching Engine: Advanced Similarity Search for Embeddings
By
–
QBE (Query-By-Example) does feature vector similarity search. Well, here's something better… @abacusai has built & deployed a Vector Matching Engine to search vector embeddings of images, documents, and more, using #DeepLearning models: http://
abacus.ai/vectormatching
*
#AI #ML #BigData