metadata
license: apache-2.0
pipeline_tag: object-detection
tags:
- pytorch
- torch-dag
Model Card for yolov8n_pruned_59
This is a prunned version of the YOLOv8n model in a toch-dag format.
This model has rougly 59% of the original model FLOPs with small metrics drop.
| Model | KMAPPs* | M Parameters | mAP50-95 (640x640) |
|---|---|---|---|
| YOLOv8n (baseline) | 21.5 | 3.16 | 37.3 |
| yolov8n_pruned_59 (ours) | 12.6 (59%) | 2.00 (63%) | 33.3 (↓ 4) |
*KMAPPs thousands of FLOPs per input pixel
KMAPPs(model) = FLOPs(model) / (H * W * 1000), where (H, W) is the input resolution.
The accuracy was calculated on the COCO val2017 dataset. For details about image pre-processing, please refer to the original repository.
Model Details
Model Description
- Developed by: TCL Research Europe
- Model type: Object detection
- License: Apache 2.0
- Finetuned from model: YOLOv8n
Model Sources
- Repository: YOLOv8n
How to Get Started with the Model
To load the model, You have to install torch-dag library, which can be done using pip by
pip install torch-dag
then, clone this repository
# Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install
git clone https://huggingface.co/TCLResearchEurope/yolov8n_pruned_59
and now You are ready to load the model:
import torch_dag
import torch
model = torch_dag.io.load_dag_from_path('./yolov8n_pruned_59')
model.eval()
out = model(torch.ones(1, 3, 224, 224))
print(out.shape)