euclidesdb
euclidesdb copied to clipboard
A multi-model machine learning feature embedding database
Due to the limitations of the PyTorch version of the prebuilt container, I wanted to build it myself by running: `docker build -t euclides_package package/` Even after modifying the whole...
Hi, thanks for creating this tool. I got an error while installation. It was on a Ubuntu GPU EC2 instance. Even though this looks like a Pytorch error, any idea...
1) Add Image grpc._channel._Rendezvous:
**Work In Progress** [![Travis](https://travis-ci.org/mycaule/euclidesdb.svg?branch=master)](https://travis-ci.org/mycaule/euclidesdb) See #6. - [ ] Structure of the folders : `/source/proto `and `python/examples/image` have to be shared at higher level in the folder hierarchy, I temporarily...
Implement integration and builds for using GPU version of libtorch.
Thank you for creating this. In case of millions or billions of feature vectors, how should we scale? Where is the index stored (in RAM or disk...)? How fast it...
I have launched EuclidesDB on local machine. Have added 48042 items into annoy index. But then I can't get similar images using `db.find_similar_image(img, ["resnet18"], 7)` ``` channel = euclides.Channel("localhost", 50000)...
The parameter `search_k` in Annoy isn't the same as the `top_k`. This must be fixed in the search engine.