30 lines
939 B
Markdown
30 lines
939 B
Markdown
---
|
|
tags:
|
|
- object-detection
|
|
---
|
|
|
|
|
|
## Model description
|
|
detr-doc-table-detection is a model trained to detect both **Bordered** and **Borderless** tables in documents, based on [facebook/detr-resnet-50](https://huggingface.co/facebook/detr-resnet-50)
|
|
|
|
## Training data
|
|
The model was trained on ICDAR2019 Table Dataset
|
|
|
|
### How to use
|
|
|
|
```python
|
|
from transformers import DetrFeatureExtractor, DetrForObjectDetection
|
|
from PIL import Image
|
|
|
|
image = Image.open("Image path")
|
|
|
|
feature_extractor = DetrFeatureExtractor.from_pretrained('TahaDouaji/detr-doc-table-detection')
|
|
model = DetrForObjectDetection.from_pretrained('TahaDouaji/detr-doc-table-detection')
|
|
|
|
inputs = feature_extractor(images=image, return_tensors="pt")
|
|
outputs = model(**inputs)
|
|
|
|
# convert outputs (bounding boxes and class logits) to COCO API
|
|
target_sizes = torch.tensor([image.size[::-1]])
|
|
results = feature_extractor.post_process(outputs, target_sizes=target_sizes)[0]
|
|
``` |