11–20 of 34 posts
While I love the efficiency from these Python to C++ ports I can't stop thinking about the long tail of subtle bugs that will likely infest these libraries forever but then the Python versions also sit atop C/C++ cores
I'm so glad the AI community is finally starting to ditch Python. It has held progress back for far too long.
I'm so glad the AI community is finally starting to ditch Python. It has held progress back for far too long.
Another popular optimisation is to port models to WASM + GPU because it makes them easy to support a variety of platforms (desktop, mobile...) with a single API and it can still offer great performance (see Google's mediapipe as an exemple of that).
While I love the efficiency from these Python to C++ ports I can't stop thinking about the long tail of subtle bugs that will likely infest these libraries forever but then the Python versions also sit atop C/C++ cores
Big fan of your work GGML friends
The Bark python model is very compute intensive and require a powerful GPU to get bearable inference speed. I really hope that bark.cpp with GPU/Metal support and quanticized model can bring useful inference speed on a laptop in the near future.
Earlier quoted context omitted.
Yes, GroundingDINO is an open set object detector. There are some others (eg DETIC and OWL-ViT) as well. We’ve been working on using them (often in conjunction with SAM) for auto-labeling datasets to train smaller faster models that can run in real-time at the edge: https://github.com/autodistill/autodistill
Would this be suitable for labeling images to search by keyword (think Apple Photos-like “car” searches to pull up photos of cars)
Really enjoyed using this app for iOS: https://github.com/mazzzystar/Queryable HN discussion: https://news.ycombinator.com/item?id=34686947
Or explore the dataset stable diffusion was trained on: https://news.ycombinator.com/item?id=32655497
I'm so glad the AI community is finally starting to ditch Python. It has held progress back for far too long.
I'm so glad the AI community is finally starting to ditch Python. It has held progress back for far too long.
Python is really great for fast prototyping. It can be argued most AI products so far are result of fast prototyping. So not sure if there is anything wrong with that.
As practical models emerge, at that point it indeed makes sense to port them to C++. But I would not in my wildest dreams suggest prototyping a data model in C++ unless absolutely necessary.
I'm so glad the AI community is finally starting to ditch Python. It has held progress back for far too long.
How has Python held it back? Most of the heavy computation lifting is done by C extensions/bindings and the models are compiled to run on CUDA, etc. What am I missing?