---
license: mit
tags:
  - object-detection
  - yolov4-tiny
  - onnx
  - int8
  - coco
  - fpga
language: en
library_name: onnxruntime
pipeline_tag: object-detection
---

# YOLOv4-tiny-416 INT8 (ONNX, MIT)

Post-training INT8 quantization of YOLOv4-tiny (Bochkovskiy et al., 2020),
exported to ONNX QOperator format. Calibrated on 1,000 COCO val2017 images.

## Files

| File | Size | SHA-256 |
|---|---:|---|
| `yolov4-tiny-416_float.onnx`     | 24,230,209 B | `eea691d460fd3eb5c1a250b4e5f822784cd44e11aaa77a24299b0952b9f4fc9f` |
| `yolov4-tiny-416_int8_qop.onnx`  |  6,113,440 B | `c30c8f0a33b3a0edc13a2ca21726a288228e1448b3c38940f9da0c7d8cee4760` |

## Architecture

| | |
|---|---|
| Layers | 21 Conv2D, 3 MaxPool, 1 Upsample, 11 Route, 2 YOLO heads |
| Activation | LeakyReLU (α = 0.1) on 19/21 convs; remaining 2 are linear (pre-head) |
| Input | 1×3×416×416, RGB, [0, 1], NCHW, letterbox-padded with 114 |
| Output | 2 raw conv tensors at strides 16 and 32 (decoder external) |
| Anchors | (10,14), (23,27), (37,58), (81,82), (135,169), (344,319) |
| Quantization | Per-tensor INT8 (W symmetric, A asymmetric); bias INT32 |

## Performance

| Metric | FP32 | INT8 | Reference (AlexeyAB) |
|---|---|---|---|
| AP @ IoU=0.5:0.95 | 0.2076 | *** | 0.217 |
| AP @ IoU=0.5      | 0.3914 | *** | 0.402 |
| AP_small          | 0.070  | *** | — |
| AP_medium         | 0.239  | *** | — |
| AP_large          | 0.325  | *** | — |
| Size              | 23.11 MiB | 5.83 MiB | — |

> *** = pending. INT8 mAP measurement on COCO val2017 is in progress;
> values will replace these markers once the evaluation completes.

### Evaluation protocol

| | |
|---|---|
| Dataset | MS COCO **val2017** (5,000 images, 36,781 annotated objects, 80 classes) |
| Annotations | `instances_val2017.json` from `annotations_trainval2017.zip` (CC BY 4.0) |
| Tool | `pycocotools.cocoeval.COCOeval` (bbox IoU type) |
| Score threshold | 0.001 (low to populate the PR curve correctly) |
| NMS | greedy, per-class, IoU threshold 0.45 |
| Detections per image | top-100 (matches `params.maxDets[2]`) |
| Image preprocessing | letterbox to 416×416, padding value 114, RGB, [0, 1], NCHW |

### Calibration protocol (for the INT8 model)

| | |
|---|---|
| Dataset | MS COCO **val2017** (1,000 images sampled) |
| Sampling | uniform random with `random.Random(42).sample(...)` (deterministic) |
| Preprocessing | identical to evaluation (letterbox 416, padding 114, RGB, /255, NCHW) |
| Quantizer | `onnxruntime.quantization.quantize_static` (MIT) |

## Reproducibility

```bash
python quantize_float_to_int8.py
python inference.py --onnx yolov4-tiny-416_int8_qop.onnx
```

The quantization script produces a bit-similar INT8 model from
`yolov4-tiny-416_float.onnx`. Differences in calibration sampling order
may shift activation scales by a few LSBs.

## Provenance

```
AlexeyAB/darknet  yolov4-tiny.weights        public domain (YOLO License v2)
        │
        │  parse_config + load_weights from gwinndr/YOLOv4-Pytorch (MIT, used as tool)
        │  + DarknetRaw wrapper to capture pre-YoloLayer outputs
        ▼
yolov4-tiny-416_float.onnx                    MIT (this repository)
        │
        │  onnxruntime.quantize_static (MIT, used as tool)
        │  + COCO val2017 calibration (CC BY 4.0, 1,000 images)
        ▼
yolov4-tiny-416_int8_qop.onnx                 MIT (this repository)
```

No Vitis-AI nor Apache-2.0 components are bundled. Tools (PyTorch, ONNX Runtime,
gwinndr) are used to produce the artifacts but not redistributed. See
`NOTICE.md` for full attribution.

## Citation

```bibtex
@article{bochkovskiy2020yolov4,
  author  = {Bochkovskiy, Alexey and Wang, Chien-Yao and Liao, Hong-Yuan Mark},
  title   = {YOLOv4: Optimal Speed and Accuracy of Object Detection},
  journal = {arXiv:2004.10934},
  year    = {2020}
}
```

Author of the INT8 derivative: **Pablo Mendoza** (`@thefalley`), 2026.