Simplify dataset download instructions

17ee7e2 verified 13 days ago

9.02 kB

---
license: unknown
library_name: ultralytics
---
# DocLayout-YOLO — Model Checkpoints

Official checkpoints for **DocLayout-YOLO**, a document-specialized real-time detector built on YOLOv12 with Page-Axis Layout Attention (PALA) and mesh-guided synthetic pretraining.

## Checkpoints

**Pretrained models** (for fine-tuning on your own layout datasets), trained on large-scale synthetic document pretraining data:

- [DocLayout-YOLO-pretrain-N.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-N.pt)
- [DocLayout-YOLO-pretrain-S.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-S.pt)
- [DocLayout-YOLO-pretrain-M.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-M.pt)
- [DocLayout-YOLO-pretrain-L.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-L.pt)
- [DocLayout-YOLO-pretrain-X.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-X.pt)

**Downstream models** (fine-tuned on four public document-layout benchmarks, five model sizes each), under [`downstream/`](./tree/main/downstream):

- [`downstream/D4LA/`](./tree/main/downstream/D4LA) · [`downstream/M6Doc/`](./tree/main/downstream/M6Doc) · [`downstream/HJDataset/`](./tree/main/downstream/HJDataset) · [`downstream/PRIMA-LAD/`](./tree/main/downstream/PRIMA-LAD)

**General-purpose model** (22 fine-grained layout categories, drop-in front-end for document parsing pipelines):

- [DocLayout-YOLO-universal.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/universal/DocLayout-YOLO-universal.pt)

Quick inference:

```python
from ultralytics import YOLO
model = YOLO("DocLayout-YOLO-universal.pt")  # download from the link above
results = model.predict("page.png", imgsz=1024, conf=0.25, iou=0.5, verbose=False)
results[0].save(filename="result.jpg")
```

Or try it online without any setup: [Online Demo (ModelScope)](https://www.modelscope.cn/studios/JulioZhao97/DocLayout-YOLO-demo).

## Main Results (mAP50-95)

| Model | D4LA | M6Doc | HJDataset | PRIMA-LAD |
| :-- | :-: | :-: | :-: | :-: |
| n | [67.2](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/n_DocLayout-YOLO.pt) | [66.2](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/n_DocLayout-YOLO.pt) | [93.6](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/n_DocLayout-YOLO.pt) | [67.7](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/n_DocLayout-YOLO.pt) |
| s | [70.6](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/s_DocLayout-YOLO.pt) | [71.1](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/s_DocLayout-YOLO.pt) | [94.8](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/s_DocLayout-YOLO.pt) | [70.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/s_DocLayout-YOLO.pt) |
| m | [70.7](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/m_DocLayout-YOLO.pt) | [73.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/m_DocLayout-YOLO.pt) | [95.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/m_DocLayout-YOLO.pt) | [71.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/m_DocLayout-YOLO.pt) |
| l | [72.4](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/l_DocLayout-YOLO.pt) | [75.1](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/l_DocLayout-YOLO.pt) | [95.7](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/l_DocLayout-YOLO.pt) | [73.4](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/l_DocLayout-YOLO.pt) |
| x | [72.4](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/x_DocLayout-YOLO.pt) | [75.5](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/x_DocLayout-YOLO.pt) | [96.0](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/x_DocLayout-YOLO.pt) | [73.1](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/x_DocLayout-YOLO.pt) |

Click a score to download the corresponding checkpoint.

## Datasets

The four downstream benchmarks are released as separate dataset repositories, each a YOLO-layout dataset directory (`images/`, `labels/`, split lists `train.txt` / `val.txt` / `test.txt`):

| dataset | repository | pages |
|:--|:--|:--|
| D4LA | [juliozhao/D4LA](https://huggingface.co/datasets/juliozhao/D4LA) | 22,184 |
| M6Doc | [juliozhao/M6Doc](https://huggingface.co/datasets/juliozhao/M6Doc) | 17,252 |
| HJDataset | [juliozhao/HJDataset](https://huggingface.co/datasets/juliozhao/HJDataset) | 4,012 |
| PRIMA-LAD | [juliozhao/PRIMA-LAD](https://huggingface.co/datasets/juliozhao/PRIMA-LAD) | 956 |

### Download

```python
# pip install huggingface_hub
from huggingface_hub import snapshot_download
for repo, local in [
    ("juliozhao/D4LA",      "D4LA"),        # keep these exact directory names
    ("juliozhao/M6Doc",     "m6doc"),       # (the val/train scripts depend on them)
    ("juliozhao/HJDataset", "HJDataset"),
    ("juliozhao/PRIMA-LAD", "prima-lad"),
]:
    snapshot_download(repo, repo_type="dataset", local_dir=local)
```

Each repository is ready to use as-is: the split lists point to the actual file locations, so no post-processing is needed after download.

## Usage

The `val.py` / `train.py` scripts referenced below ship in the release package. Typical flows:

**Validation** (dataset root = the parent directory holding the four dataset folders):

```bash
python val.py --model downstream/PRIMA-LAD/s_DocLayout-YOLO.pt \
  --data prima-lad --dataset-root /absolute/path/to/datasets
```

`--data` accepts one of the dataset aliases `d4la` | `m6doc` | `hjdataset` | `prima-lad`.

**Fine-tuning** from a pretrained checkpoint:

```bash
python train.py --data ultralytics/cfg/datasets/D4LA.yaml \
  --pretrain DocLayout-YOLO-pretrain-X.pt \
  --epoch 500 --image-size 1600 --batch-size 64 --project runs
```

**Prediction**:

```python
from ultralytics import YOLO
model = YOLO("downstream/M6Doc/m_DocLayout-YOLO.pt")
results = model.predict("page.png", imgsz=1600, conf=0.25, device="cuda:0")
results[0].save(filename="result.jpg")
```

## SHA256 (first 16 hex chars)

| repo path | sha256 (16) | size (MB) |
|---|---|---|
| `DocLayout-YOLO-pretrain-N.pt` | `178a9ff51e3cd848` | 9.6 |
| `DocLayout-YOLO-pretrain-S.pt` | `f203c9d02740a549` | 35.8 |
| `DocLayout-YOLO-pretrain-M.pt` | `bfbec6286ef2f659` | 79.3 |
| `DocLayout-YOLO-pretrain-L.pt` | `da336fad052f7ff2` | 107.0 |
| `DocLayout-YOLO-pretrain-X.pt` | `fe0d4daef3d14c8a` | 238.6 |
| `downstream/D4LA/n_DocLayout-YOLO.pt` | `ddc1189beed91e27` | 5.0 |
| `downstream/D4LA/s_DocLayout-YOLO.pt` | `a1d0f8efe22580f3` | 18.2 |
| `downstream/D4LA/m_DocLayout-YOLO.pt` | `ecff5e042e03626b` | 39.9 |
| `downstream/D4LA/l_DocLayout-YOLO.pt` | `826ec4281d1064a2` | 53.9 |
| `downstream/D4LA/x_DocLayout-YOLO.pt` | `fa1d38605ee26115` | 119.8 |
| `downstream/M6Doc/n_DocLayout-YOLO.pt` | `62e3c9352a050769` | 5.0 |
| `downstream/M6Doc/s_DocLayout-YOLO.pt` | `7ce579090a2a0d51` | 18.1 |
| `downstream/M6Doc/m_DocLayout-YOLO.pt` | `e0b3f0356ed4bb6e` | 40.0 |
| `downstream/M6Doc/l_DocLayout-YOLO.pt` | `f4cf7b8e56978ade` | 53.9 |
| `downstream/M6Doc/x_DocLayout-YOLO.pt` | `bddd9e3ebb10a412` | 119.8 |
| `downstream/HJDataset/n_DocLayout-YOLO.pt` | `1099870f0b82c01f` | 5.0 |
| `downstream/HJDataset/s_DocLayout-YOLO.pt` | `6044020c8f13d5de` | 18.2 |
| `downstream/HJDataset/m_DocLayout-YOLO.pt` | `65cf6375760cb08b` | 39.9 |
| `downstream/HJDataset/l_DocLayout-YOLO.pt` | `5878bc467353c810` | 53.9 |
| `downstream/HJDataset/x_DocLayout-YOLO.pt` | `7dd575f4115537ea` | 119.7 |
| `downstream/PRIMA-LAD/n_DocLayout-YOLO.pt` | `f21f9a798a021374` | 5.0 |
| `downstream/PRIMA-LAD/s_DocLayout-YOLO.pt` | `4e9177b75a3c825c` | 18.2 |
| `downstream/PRIMA-LAD/m_DocLayout-YOLO.pt` | `1fcccb0f9273d83a` | 39.9 |
| `downstream/PRIMA-LAD/l_DocLayout-YOLO.pt` | `38fb188c3567d033` | 53.9 |
| `downstream/PRIMA-LAD/x_DocLayout-YOLO.pt` | `d79b8c6f9af4e47a` | 119.7 |
| `universal/DocLayout-YOLO-universal.pt` | `5c733afe7481aea1` | 119.6 |

## License

The source code is distributed under the GNU Affero General Public License v3.0 (AGPL-3.0).

## Citation

```BibTeX
@misc{zhao2024doclayoutyoloenhancingdocumentlayout,
      title={DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception},
      author={Zhiyuan Zhao and Hengrui Kang and Bin Wang and Conghui He},
      year={2024},
      eprint={2410.12628},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2410.12628},
}
```

	---
	license: unknown
	library_name: ultralytics
	---

	# DocLayout-YOLO — Model Checkpoints

	Official checkpoints for DocLayout-YOLO, a document-specialized real-time detector built on YOLOv12 with Page-Axis Layout Attention (PALA) and mesh-guided synthetic pretraining.

	## Checkpoints

	Pretrained models (for fine-tuning on your own layout datasets), trained on large-scale synthetic document pretraining data:

	- [DocLayout-YOLO-pretrain-N.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-N.pt)
	- [DocLayout-YOLO-pretrain-S.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-S.pt)
	- [DocLayout-YOLO-pretrain-M.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-M.pt)
	- [DocLayout-YOLO-pretrain-L.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-L.pt)
	- [DocLayout-YOLO-pretrain-X.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/DocLayout-YOLO-pretrain-X.pt)

	Downstream models (fine-tuned on four public document-layout benchmarks, five model sizes each), under [`downstream/`](./tree/main/downstream):

	- [`downstream/D4LA/`](./tree/main/downstream/D4LA) · [`downstream/M6Doc/`](./tree/main/downstream/M6Doc) · [`downstream/HJDataset/`](./tree/main/downstream/HJDataset) · [`downstream/PRIMA-LAD/`](./tree/main/downstream/PRIMA-LAD)

	General-purpose model (22 fine-grained layout categories, drop-in front-end for document parsing pipelines):

	- [DocLayout-YOLO-universal.pt](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/universal/DocLayout-YOLO-universal.pt)

	Quick inference:

	```python
	from ultralytics import YOLO

	model = YOLO("DocLayout-YOLO-universal.pt") # download from the link above
	results = model.predict("page.png", imgsz=1024, conf=0.25, iou=0.5, verbose=False)
	results[0].save(filename="result.jpg")
	```

	Or try it online without any setup: [Online Demo (ModelScope)](https://www.modelscope.cn/studios/JulioZhao97/DocLayout-YOLO-demo).

	## Main Results (mAP50-95)

	\| Model \| D4LA \| M6Doc \| HJDataset \| PRIMA-LAD \|
	\| :-- \| :-: \| :-: \| :-: \| :-: \|
	\| n \| [67.2](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/n_DocLayout-YOLO.pt) \| [66.2](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/n_DocLayout-YOLO.pt) \| [93.6](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/n_DocLayout-YOLO.pt) \| [67.7](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/n_DocLayout-YOLO.pt) \|
	\| s \| [70.6](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/s_DocLayout-YOLO.pt) \| [71.1](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/s_DocLayout-YOLO.pt) \| [94.8](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/s_DocLayout-YOLO.pt) \| [70.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/s_DocLayout-YOLO.pt) \|
	\| m \| [70.7](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/m_DocLayout-YOLO.pt) \| [73.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/m_DocLayout-YOLO.pt) \| [95.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/m_DocLayout-YOLO.pt) \| [71.3](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/m_DocLayout-YOLO.pt) \|
	\| l \| [72.4](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/l_DocLayout-YOLO.pt) \| [75.1](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/l_DocLayout-YOLO.pt) \| [95.7](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/l_DocLayout-YOLO.pt) \| [73.4](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/l_DocLayout-YOLO.pt) \|
	\| x \| [72.4](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/D4LA/x_DocLayout-YOLO.pt) \| [75.5](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/M6Doc/x_DocLayout-YOLO.pt) \| [96.0](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/HJDataset/x_DocLayout-YOLO.pt) \| [73.1](https://huggingface.co/juliozhao/DocLayout-YOLO/resolve/main/downstream/PRIMA-LAD/x_DocLayout-YOLO.pt) \|

	Click a score to download the corresponding checkpoint.

	## Datasets

	The four downstream benchmarks are released as separate dataset repositories, each a YOLO-layout dataset directory (`images/`, `labels/`, split lists `train.txt` / `val.txt` / `test.txt`):

	\| dataset \| repository \| pages \|
	\|:--\|:--\|:--\|
	\| D4LA \| [juliozhao/D4LA](https://huggingface.co/datasets/juliozhao/D4LA) \| 22,184 \|
	\| M6Doc \| [juliozhao/M6Doc](https://huggingface.co/datasets/juliozhao/M6Doc) \| 17,252 \|
	\| HJDataset \| [juliozhao/HJDataset](https://huggingface.co/datasets/juliozhao/HJDataset) \| 4,012 \|
	\| PRIMA-LAD \| [juliozhao/PRIMA-LAD](https://huggingface.co/datasets/juliozhao/PRIMA-LAD) \| 956 \|

	### Download

	```python
	# pip install huggingface_hub
	from huggingface_hub import snapshot_download

	for repo, local in [
	("juliozhao/D4LA", "D4LA"), # keep these exact directory names
	("juliozhao/M6Doc", "m6doc"), # (the val/train scripts depend on them)
	("juliozhao/HJDataset", "HJDataset"),
	("juliozhao/PRIMA-LAD", "prima-lad"),
	]:
	snapshot_download(repo, repo_type="dataset", local_dir=local)
	```

	Each repository is ready to use as-is: the split lists point to the actual file locations, so no post-processing is needed after download.

	## Usage

	The `val.py` / `train.py` scripts referenced below ship in the release package. Typical flows:

	Validation (dataset root = the parent directory holding the four dataset folders):

	```bash
	python val.py --model downstream/PRIMA-LAD/s_DocLayout-YOLO.pt \
	--data prima-lad --dataset-root /absolute/path/to/datasets
	```

	`--data` accepts one of the dataset aliases `d4la` \| `m6doc` \| `hjdataset` \| `prima-lad`.

	Fine-tuning from a pretrained checkpoint:

	```bash
	python train.py --data ultralytics/cfg/datasets/D4LA.yaml \
	--pretrain DocLayout-YOLO-pretrain-X.pt \
	--epoch 500 --image-size 1600 --batch-size 64 --project runs
	```

	Prediction:

	```python
	from ultralytics import YOLO

	model = YOLO("downstream/M6Doc/m_DocLayout-YOLO.pt")
	results = model.predict("page.png", imgsz=1600, conf=0.25, device="cuda:0")
	results[0].save(filename="result.jpg")
	```

	## SHA256 (first 16 hex chars)

	\| repo path \| sha256 (16) \| size (MB) \|
	\|---\|---\|---\|
	\| `DocLayout-YOLO-pretrain-N.pt` \| `178a9ff51e3cd848` \| 9.6 \|
	\| `DocLayout-YOLO-pretrain-S.pt` \| `f203c9d02740a549` \| 35.8 \|
	\| `DocLayout-YOLO-pretrain-M.pt` \| `bfbec6286ef2f659` \| 79.3 \|
	\| `DocLayout-YOLO-pretrain-L.pt` \| `da336fad052f7ff2` \| 107.0 \|
	\| `DocLayout-YOLO-pretrain-X.pt` \| `fe0d4daef3d14c8a` \| 238.6 \|
	\| `downstream/D4LA/n_DocLayout-YOLO.pt` \| `ddc1189beed91e27` \| 5.0 \|
	\| `downstream/D4LA/s_DocLayout-YOLO.pt` \| `a1d0f8efe22580f3` \| 18.2 \|
	\| `downstream/D4LA/m_DocLayout-YOLO.pt` \| `ecff5e042e03626b` \| 39.9 \|
	\| `downstream/D4LA/l_DocLayout-YOLO.pt` \| `826ec4281d1064a2` \| 53.9 \|
	\| `downstream/D4LA/x_DocLayout-YOLO.pt` \| `fa1d38605ee26115` \| 119.8 \|
	\| `downstream/M6Doc/n_DocLayout-YOLO.pt` \| `62e3c9352a050769` \| 5.0 \|
	\| `downstream/M6Doc/s_DocLayout-YOLO.pt` \| `7ce579090a2a0d51` \| 18.1 \|
	\| `downstream/M6Doc/m_DocLayout-YOLO.pt` \| `e0b3f0356ed4bb6e` \| 40.0 \|
	\| `downstream/M6Doc/l_DocLayout-YOLO.pt` \| `f4cf7b8e56978ade` \| 53.9 \|
	\| `downstream/M6Doc/x_DocLayout-YOLO.pt` \| `bddd9e3ebb10a412` \| 119.8 \|
	\| `downstream/HJDataset/n_DocLayout-YOLO.pt` \| `1099870f0b82c01f` \| 5.0 \|
	\| `downstream/HJDataset/s_DocLayout-YOLO.pt` \| `6044020c8f13d5de` \| 18.2 \|
	\| `downstream/HJDataset/m_DocLayout-YOLO.pt` \| `65cf6375760cb08b` \| 39.9 \|
	\| `downstream/HJDataset/l_DocLayout-YOLO.pt` \| `5878bc467353c810` \| 53.9 \|
	\| `downstream/HJDataset/x_DocLayout-YOLO.pt` \| `7dd575f4115537ea` \| 119.7 \|
	\| `downstream/PRIMA-LAD/n_DocLayout-YOLO.pt` \| `f21f9a798a021374` \| 5.0 \|
	\| `downstream/PRIMA-LAD/s_DocLayout-YOLO.pt` \| `4e9177b75a3c825c` \| 18.2 \|
	\| `downstream/PRIMA-LAD/m_DocLayout-YOLO.pt` \| `1fcccb0f9273d83a` \| 39.9 \|
	\| `downstream/PRIMA-LAD/l_DocLayout-YOLO.pt` \| `38fb188c3567d033` \| 53.9 \|
	\| `downstream/PRIMA-LAD/x_DocLayout-YOLO.pt` \| `d79b8c6f9af4e47a` \| 119.7 \|
	\| `universal/DocLayout-YOLO-universal.pt` \| `5c733afe7481aea1` \| 119.6 \|

	## License

	The source code is distributed under the GNU Affero General Public License v3.0 (AGPL-3.0).

	## Citation

	```BibTeX
	@misc{zhao2024doclayoutyoloenhancingdocumentlayout,
	title={DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception},
	author={Zhiyuan Zhao and Hengrui Kang and Bin Wang and Conghui He},
	year={2024},
	eprint={2410.12628},
	archivePrefix={arXiv},
	primaryClass={cs.CV},
	url={https://arxiv.org/abs/2410.12628},
	}
	```