Commit
•
82b0136
1
Parent(s):
fc0a115
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,8 +8,6 @@ tags:
|
|
| 8 |
|
| 9 |
# Model Details
|
| 10 |
|
| 11 |
-
## Model Description
|
| 12 |
-
|
| 13 |
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).
|
| 14 |
|
| 15 |
- **Developed by:** Taha Douaji
|
|
@@ -30,10 +28,6 @@ detr-doc-table-detection is a model trained to detect both **Bordered** and **Bo
|
|
| 30 |
## Direct Use
|
| 31 |
This model can be used for the task of object detection.
|
| 32 |
|
| 33 |
-
## Downstream Use [Optional]
|
| 34 |
-
|
| 35 |
-
More information needed.
|
| 36 |
-
|
| 37 |
## Out-of-Scope Use
|
| 38 |
|
| 39 |
The model should not be used to intentionally create hostile or alienating environments for people.
|
|
@@ -59,14 +53,6 @@ The model was trained on ICDAR2019 Table Dataset
|
|
| 59 |
## Training Procedure
|
| 60 |
|
| 61 |
|
| 62 |
-
### Preprocessing
|
| 63 |
-
|
| 64 |
-
More information needed
|
| 65 |
-
|
| 66 |
-
### Speeds, Sizes, Times
|
| 67 |
-
More information needed
|
| 68 |
-
|
| 69 |
-
|
| 70 |
# Evaluation
|
| 71 |
|
| 72 |
|
|
@@ -172,9 +158,7 @@ More information needed
|
|
| 172 |
# How to Get Started with the Model
|
| 173 |
|
| 174 |
Use the code below to get started with the model.
|
| 175 |
-
|
| 176 |
-
<details>
|
| 177 |
-
<summary> Click to expand </summary>
|
| 178 |
|
| 179 |
```python
|
| 180 |
from transformers import DetrImageProcessor, DetrForObjectDetection
|
|
@@ -202,5 +186,4 @@ for score, label, box in zip(results["scores"], results["labels"], results["boxe
|
|
| 202 |
f"Detected {model.config.id2label[label.item()]} with confidence "
|
| 203 |
f"{round(score.item(), 3)} at location {box}"
|
| 204 |
)
|
| 205 |
-
```
|
| 206 |
-
</details>
|
|
|
|
| 8 |
|
| 9 |
# Model Details
|
| 10 |
|
|
|
|
|
|
|
| 11 |
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).
|
| 12 |
|
| 13 |
- **Developed by:** Taha Douaji
|
|
|
|
| 28 |
## Direct Use
|
| 29 |
This model can be used for the task of object detection.
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## Out-of-Scope Use
|
| 32 |
|
| 33 |
The model should not be used to intentionally create hostile or alienating environments for people.
|
|
|
|
| 53 |
## Training Procedure
|
| 54 |
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
# Evaluation
|
| 57 |
|
| 58 |
|
|
|
|
| 158 |
# How to Get Started with the Model
|
| 159 |
|
| 160 |
Use the code below to get started with the model.
|
| 161 |
+
|
|
|
|
|
|
|
| 162 |
|
| 163 |
```python
|
| 164 |
from transformers import DetrImageProcessor, DetrForObjectDetection
|
|
|
|
| 186 |
f"Detected {model.config.id2label[label.item()]} with confidence "
|
| 187 |
f"{round(score.item(), 3)} at location {box}"
|
| 188 |
)
|
| 189 |
+
```
|
|
|