carpedm20/DEIMv2
By carpedm20 · ↓ 0 · ♥ 0 · Updated 2026-01-20
What's in this repo
This page lists the files in carpedm20/DEIMv2, including deimv2_dinov3_l_coco.onnx, deimv2_dinov3_m_coco.onnx, deimv2_dinov3_s_coco.onnx and more.
- 8 ONNX models (.onnx files)
- 34 files, including 8 .engine, 8 .log, 8 .onnx, 8 .pth, 1 .md
- Last updated 2026-01-20
ONNX files
| File | Size | Download |
|---|---|---|
| deimv2_dinov3_l_coco.onnx | — | Download |
| deimv2_dinov3_m_coco.onnx | — | Download |
| deimv2_dinov3_s_coco.onnx | — | Download |
| deimv2_dinov3_x_coco.onnx | — | Download |
| deimv2_hgnetv2_atto_coco.onnx | — | Download |
| deimv2_hgnetv2_femto_coco.onnx | — | Download |
| deimv2_hgnetv2_n_coco.onnx | — | Download |
| deimv2_hgnetv2_pico_coco.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
DEIMv2 - Real-Time Object Detection Meets DINOv3
Pre-trained DEIMv2 models with PyTorch checkpoints, ONNX exports, and TensorRT FP16 engines.
Model Zoo
| Model | AP | Params | GFLOPs | Checkpoint | ONNX | TensorRT |
|---|---|---|---|---|---|---|
| Atto | 23.8 | 0.5M | 0.8 | ✅ | ✅ | ✅ |
| Femto | 31.0 | 1.0M | 1.7 | ✅ | ✅ | ✅ |
| Pico | 38.5 | 1.5M | 5.2 | ✅ | ✅ | ✅ |
| N | 43.0 | 3.6M | 6.8 | ✅ | ✅ | ✅ |
| S | 50.9 | 9.7M | 25.6 | ✅ | ✅ | ✅ |
| M | 53.0 | 18.1M | 52.2 | ✅ | ✅ | ✅ |
| L | 56.0 | 32.2M | 96.7 | ✅ | ✅ | ✅ |
| X | 57.8 | 50.3M | 151.6 | ✅ | ✅ | ✅ |
Files
*.pth- PyTorch checkpoints (EMA weights)*.onnx- ONNX models (opset 17, dynamic batch)*.engine- TensorRT FP16 engines (built on RTX 4090, TensorRT 10.14)
Input Shapes
| Model | Input Size |
|---|---|
| Atto | 320x320 |
| Femto | 416x416 |
| Pico, N, S, M, L, X | 640x640 |
Usage
PyTorch
from huggingface_hub import hf_hub_download
import torch
# Download checkpoint
ckpt_path = hf_hub_download("carpedm20/DEIMv2", "deimv2_dinov3_s_coco.pth")
checkpoint = torch.load(ckpt_path, map_location='cpu')
state_dict = checkpoint['ema']['module']
ONNX Runtime
import onnxruntime as ort
from huggingface_hub import hf_hub_download
onnx_path = hf_hub_download("carpedm20/DEIMv2", "deimv2_dinov3_s_coco.onnx")
session = ort.InferenceSession(onnx_path)
TensorRT
import tensorrt as trt
from huggingface_hub import hf_hub_download
engine_path = hf_hub_download("carpedm20/DEIMv2", "deimv2_dinov3_s_coco.engine")
# Load engine with TensorRT runtime
Citation
@article{huang2025deimv2,
title={Real-Time Object Detection Meets DINOv3},
author={Huang, Shihua and Hou, Yongjie and Liu, Longfei and Yu, Xuanlong and Shen, Xi},
journal={arXiv},
year={2025}
}
License
Apache 2.0 - See DEIMv2 GitHub for details.
Model info
Created: 2026-01-20
Updated: 2026-01-20
View on Hugging FaceFiles (34)
Related models
More from carpedm20
No other models by this author.