Instructions to use Bilgee/detr-finetuned-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Bilgee/detr-finetuned-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="Bilgee/detr-finetuned-v2")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("Bilgee/detr-finetuned-v2") model = AutoModelForObjectDetection.from_pretrained("Bilgee/detr-finetuned-v2") - Notebooks
- Google Colab
- Kaggle
Upload TableTransformerForObjectDetection
Browse files- config.json +1 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
@@ -50,7 +50,6 @@
|
|
| 50 |
"mask_loss_coefficient": 1,
|
| 51 |
"max_position_embeddings": 1024,
|
| 52 |
"model_type": "table-transformer",
|
| 53 |
-
"normalize_before": true,
|
| 54 |
"num_channels": 3,
|
| 55 |
"num_hidden_layers": 6,
|
| 56 |
"num_queries": 125,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/table-transformer-structure-recognition",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
|
|
|
| 50 |
"mask_loss_coefficient": 1,
|
| 51 |
"max_position_embeddings": 1024,
|
| 52 |
"model_type": "table-transformer",
|
|
|
|
| 53 |
"num_channels": 3,
|
| 54 |
"num_hidden_layers": 6,
|
| 55 |
"num_queries": 125,
|