# DEIMv2.axera

[DEIMv2](https://github.com/Intellindust-AI-Lab/DEIMv2) Real-Time Object Detection Meets DINOv3, running on Axera NPU (AX650).

![demo](assets/demo.jpg)

This repo contains the deployment-ready ONNX graph, the Pulsar2 build configuration, calibration data, and a minimal inference script.

| Model | Note |
| ----- | ---- |
| [`deimv2_pico.onnx`](onnx/deimv2_pico.onnx) | DEIMv2-HGNetv2-Pico, 640x640, with in-graph post-processing. |
| [`deimv2_s.onnx`](onnx/deimv2_s.onnx) | DEIMv2-DINOv3-S, 640x640, with in-graph post-processing. |
| [`deimv2_x.onnx`](onnx/deimv2_x.onnx) | DEIMv2-DINOv3-X, 640x640, with in-graph post-processing |

## Results

COCO val2017 (all 5,000 images), bbox mAP@`0.50:0.95` using COCOeval and a score threshold of 0.001. The axmodels were evaluated on an AX650A board in NPU1 mode.

| Model | Official FP32 ONNX | AX650A axmodel | NPU1 Latency(ms) | NPU3 Latency(ms) |
| ----- | ------------------: | -------------: | -----------------: |-------------: |
| Pico | 0.384 | 0.375 | ~10.193 | 5.389 |
| S | 0.506 | 0.506 | ~155 | 42.395 |
| X | 0.567 | 0.577 | ~355 | ~118 |

## Build

Requires the Axera Pulsar2 toolchain (`pulsar2`).

```bash
pulsar2 build --config config.json --input onnx/deimv2_s.onnx
```

## Inference on board

Copy `compiled.axmodel`, `infer.py` and a test image to the board, then:

```bash
python3 infer.py -m compiled.axmodel -i test.jpg
```
Or
```bash
python3 infer.py -m compiled.axmodel -d /path/to/images --thr 0.6 -o vis/
```

Dependencies on board: `axengine`, `numpy`, `Pillow`.

On PC (FP32 reference):

```bash
python3 infer.py -m onnx/deimv2_s.onnx -i test.jpg
```
## Note: freezing `orig_target_sizes` for production

`orig_target_sizes` only tells the post-processor how to scale boxes back to the
original image size. If your deployment always feeds images of one fixed
resolution (e.g. a 1920x1080 camera stream), you can hard-code it and drop the
second input: in the ONNX graph, replace the `orig_target_sizes` graph input
with an initializer holding `[w, h]`, remove the matching `input_configs` entry
from `config.json`, and rebuild. Do **not** do this if input resolutions vary —
boxes would be scaled with the wrong size.

## License

BSD 3-Clause License. See [LICENSE](LICENSE).