Object Detection
Transformers
ONNX
Chinese
English
document-ai
document-layout-analysis
patent
pdf
hiro
patsnap
Instructions to use PatSnap/Hiro-Layout with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PatSnap/Hiro-Layout with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="PatSnap/Hiro-Layout")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("PatSnap/Hiro-Layout", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update model card and clean release files
Browse files- .gitignore +2 -0
- EVALUATION.md +1 -1
- README.md +0 -2
- README_zh.md +0 -2
.gitignore
CHANGED
|
@@ -7,4 +7,6 @@ __pycache__/
|
|
| 7 |
.venv/
|
| 8 |
venv/
|
| 9 |
env/
|
|
|
|
| 10 |
outputs/
|
|
|
|
|
|
| 7 |
.venv/
|
| 8 |
venv/
|
| 9 |
env/
|
| 10 |
+
python=*/
|
| 11 |
outputs/
|
| 12 |
+
layout模型benchmark.xlsx
|
EVALUATION.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
# Evaluation Results
|
| 2 |
|
| 3 |
-
The
|
| 4 |
|
| 5 |
- `Patent PDF`
|
| 6 |
- `NPD PDF`
|
|
|
|
| 1 |
# Evaluation Results
|
| 2 |
|
| 3 |
+
The benchmark contains two evaluation sets:
|
| 4 |
|
| 5 |
- `Patent PDF`
|
| 6 |
- `NPD PDF`
|
README.md
CHANGED
|
@@ -43,7 +43,6 @@ Hiro-Layout is a document layout analysis model for patent and technical PDF pag
|
|
| 43 |
| Output | Layout regions with class labels |
|
| 44 |
| Domains | Patent PDFs, technical/NPD PDFs |
|
| 45 |
| License | Apache-2.0 |
|
| 46 |
-
| Evaluation file | `layout模型benchmark.xlsx` |
|
| 47 |
|
| 48 |
## Layout Taxonomy
|
| 49 |
|
|
@@ -174,7 +173,6 @@ Use `labels.json` for the 25-class label mapping.
|
|
| 174 |
| `README_zh.md` | Chinese model card |
|
| 175 |
| `EVALUATION.md` | Detailed benchmark results derived from the workbook |
|
| 176 |
| `labels.json` | Machine-readable 25-class label mapping |
|
| 177 |
-
| `layout模型benchmark.xlsx` | Source evaluation workbook |
|
| 178 |
| `layout_model/RT-DETR_25.onnx` | ONNX model artifact |
|
| 179 |
| `requirements.txt` | Minimal dependencies for ONNX loading and image preprocessing |
|
| 180 |
| `LICENSE` | Apache-2.0 license |
|
|
|
|
| 43 |
| Output | Layout regions with class labels |
|
| 44 |
| Domains | Patent PDFs, technical/NPD PDFs |
|
| 45 |
| License | Apache-2.0 |
|
|
|
|
| 46 |
|
| 47 |
## Layout Taxonomy
|
| 48 |
|
|
|
|
| 173 |
| `README_zh.md` | Chinese model card |
|
| 174 |
| `EVALUATION.md` | Detailed benchmark results derived from the workbook |
|
| 175 |
| `labels.json` | Machine-readable 25-class label mapping |
|
|
|
|
| 176 |
| `layout_model/RT-DETR_25.onnx` | ONNX model artifact |
|
| 177 |
| `requirements.txt` | Minimal dependencies for ONNX loading and image preprocessing |
|
| 178 |
| `LICENSE` | Apache-2.0 license |
|
README_zh.md
CHANGED
|
@@ -43,7 +43,6 @@ Hiro-Layout 是一个面向专利和技术 PDF 页面图像的文档版面分析
|
|
| 43 |
| 输出 | 带类别标签的版面区域 |
|
| 44 |
| 领域 | 专利 PDF、技术/NPD PDF |
|
| 45 |
| 开源协议 | Apache-2.0 |
|
| 46 |
-
| 评测文件 | `layout模型benchmark.xlsx` |
|
| 47 |
|
| 48 |
## 类别体系
|
| 49 |
|
|
@@ -174,7 +173,6 @@ print("outputs:", [o.name for o in session.get_outputs()])
|
|
| 174 |
| `README_zh.md` | 中文模型卡 |
|
| 175 |
| `EVALUATION.md` | 从 Excel 整理出的详细评测结果 |
|
| 176 |
| `labels.json` | 机器可读的 25 类标签映射 |
|
| 177 |
-
| `layout模型benchmark.xlsx` | 原始评测 Excel |
|
| 178 |
| `layout_model/RT-DETR_25.onnx` | ONNX 模型文件 |
|
| 179 |
| `requirements.txt` | ONNX 加载和图像预处理的最小依赖 |
|
| 180 |
| `LICENSE` | Apache-2.0 协议 |
|
|
|
|
| 43 |
| 输出 | 带类别标签的版面区域 |
|
| 44 |
| 领域 | 专利 PDF、技术/NPD PDF |
|
| 45 |
| 开源协议 | Apache-2.0 |
|
|
|
|
| 46 |
|
| 47 |
## 类别体系
|
| 48 |
|
|
|
|
| 173 |
| `README_zh.md` | 中文模型卡 |
|
| 174 |
| `EVALUATION.md` | 从 Excel 整理出的详细评测结果 |
|
| 175 |
| `labels.json` | 机器可读的 25 类标签映射 |
|
|
|
|
| 176 |
| `layout_model/RT-DETR_25.onnx` | ONNX 模型文件 |
|
| 177 |
| `requirements.txt` | ONNX 加载和图像预处理的最小依赖 |
|
| 178 |
| `LICENSE` | Apache-2.0 协议 |
|