Instructions to use LeBrony/mekanet-release-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use LeBrony/mekanet-release-weights with ultralytics:
from huggingface_hub import hf_hub_download from ultralytics import YOLO # pick the weights file from this repo's "Files and versions" tab weights = hf_hub_download("LeBrony/mekanet-release-weights", "<weights>.pt") model = YOLO(weights) source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
MekaNet Detection Weights
This repository hosts public weight artifacts for the MekaNet manuscript-aligned release.
Included artifact
epoch60.pt: YOLOv8 detection checkpoint for megakaryocyte detection
Provenance
- Source code repository:
LeGenAI/mekanet-release - Manuscript file:
mekanet_medical.tex - Intended public release consumer: reviewers and readers validating the detection pipeline
License
This model artifact is distributed for research, manuscript review, and reproducibility verification only.
- no clinical deployment
- no commercial deployment
- no representation of regulatory approval
- preserve attribution and license notice on redistribution
See the repository LICENSE file in this Hugging Face model repo for the controlling terms.
Integrity
epoch60.ptSHA-256:dc3b411530457815219a6549587cf18f57590e4d77c859597c9647d176568d53
Usage
from mekanet.models.yolo_sahi import YoloSahiDetector
detector = YoloSahiDetector("epoch60.pt", confidence_threshold=0.20, device="cpu")
Notes
- This weight artifact is distributed separately from the main code repository to keep the public code release lightweight and reviewer-friendly.
- The main repository uses a manifest-driven downloader and checksum verification.
- Downloads last month
- 13