Instructions to use alonsorobots/scrfd_320_batched with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TensorRT
How to use alonsorobots/scrfd_320_batched with TensorRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Request: Batched ONNX export for scrfd_500m
#1
by abushahid - opened
Hi, thanks for putting this together β the contamination fix and proper dynamic_axes export is exactly what was missing from the original InsightFace repo.
I noticed you've re-exported scrfd_10g but not the lighter models. Any chance you could provide a batched export of scrfd_500m as well? The 10g model is overkill for our use case (we're running on edge hardware with a tight latency budget), and having the same dynamic batch support on 500m would be really useful.
Happy to test and report back if you do publish it.