Instructions to use TusharGoel/LayoutLMv2-finetuned-docvqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TusharGoel/LayoutLMv2-finetuned-docvqa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("document-question-answering", model="TusharGoel/LayoutLMv2-finetuned-docvqa")# Load model directly from transformers import AutoProcessor, AutoModelForDocumentQuestionAnswering processor = AutoProcessor.from_pretrained("TusharGoel/LayoutLMv2-finetuned-docvqa") model = AutoModelForDocumentQuestionAnswering.from_pretrained("TusharGoel/LayoutLMv2-finetuned-docvqa") - Notebooks
- Google Colab
- Kaggle
Commit ·
7bb3b36
1
Parent(s): 99874f2
Upload preprocessor_config.json
Browse files- preprocessor_config.json +7 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_ocr": false,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "LayoutLMv2FeatureExtractor",
|
| 5 |
+
"resample": 2,
|
| 6 |
+
"size": 224
|
| 7 |
+
}
|