imgbeddings
torchgeo
Our great sponsors
imgbeddings | torchgeo | |
---|---|---|
8 | 2 | |
122 | 2,223 | |
- | 4.4% | |
0.0 | 9.7 | |
about 2 years ago | 3 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
imgbeddings
- FLaNK Stack Weekly for 20 Nov 2023
-
Content-Based Image Retrieval
Seconding the recommendation of CLIP embeddings, especially compared to image histograms + requiring OpenCV.
I wrote a naive, minimal dependency Python package to calculate image embeddings (https://github.com/minimaxir/imgbeddings) with some lookup demo notebooks and it works well in a pinch, although it's due for an upgrade.
-
How to build a working AI only using synthetic data in just 5 minutes
Normally, this is Hacker News reductiveness, but yes, image classification via CLIP is that easy, especially with Hugging Face's API for it: https://huggingface.co/docs/transformers/model_doc/clip
I created a Python package to generate image embeddings from CLIP's vision model (without requiring a ML framework), and a simple linear classifier on those embeddings does the trick: https://github.com/minimaxir/imgbeddings
- GitHub - minimaxir/imgbeddings: Python package to generate image embeddings with CLIP without PyTorch/TensorFlow
- Show HN: Python package to create image embeddings without PyTorch/TensorFlow
- I've released a Python package which lets you generate vector representations of images clustering/similarity search/classifier building with a twist: neither PyTorch nor TensorFlow is used!
- [P] I've released a Python package which lets you generate vector representations of images with a twist: neither PyTorch nor TensorFlow is used!
- Show HN: Python package to create image embeddings with o PyTorch/TensorFlow
torchgeo
- FLaNK Stack Weekly for 20 Nov 2023
-
Ask HN: What are your goals for 2023?
Considering something like torchgeo (https://github.com/microsoft/torchgeo), or maybe some geospatial library written in Julia.
> but the problem I have is that everything seems to just work and I don't run into many issues to fix.
May I point you at linux audio? ;-) Getting any type of DAW working in linux without having to do some crazy rewiring with jack would be a godsend.
What are some alternatives?
ai-music - A vanilla Trasformer Decoder music generation model trained on Final Fantasy OST MIDI songs
facetorch - Python library for analysing faces using PyTorch
TwoPhotosOnA6x4 - Stitches 2 photos for printing on a 6"x4" photo.
torchSR - Super Resolution datasets and models in Pytorch
FLaNK-EveryTransitSystem - Every transit system
pgmq - A lightweight message queue. Like AWS SQS and RSMQ but on Postgres.
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
merged_depth - Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models
screenshot-to-code - Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
dalle2-in-python - Use DALLĀ·E 2 in Python
CML_AMP-Text-to-Image-with-Stable-Diffusion - CML AMP Text-to-Image with Stable Diffusion