Add onnxtr-tablecenternet model

README.md

@@ -0,0 +1,56 @@
+---
+language:
+- en
+- fr
+license: apache-2.0
+tags:
+- ocr
+- onnx
+- onnxtr
+- table_structure
+---
+
+<p align="center">
+<img src="https://github.com/felixdittrich92/OnnxTR/raw/main/docs/images/logo.jpg" width="40%">
+</p>
+
+**Optical Character Recognition made seamless & accessible to anyone, powered by Onnxruntime**
+
+## Task: table_structure
+
+https://github.com/felixdittrich92/OnnxTR
+
+### Example usage:
+
+```python
+>>> from onnxtr.io import DocumentFile
+>>> from onnxtr.models import ocr_predictor, from_hub
+
+>>> img = DocumentFile.from_images(['<image_path>'])
+>>> # Load your model from the hub
+>>> model = from_hub('onnxtr/my-model')
+
+>>> # Pass it to the predictor
+>>> # If your model is a recognition model:
+>>> predictor = ocr_predictor(det_arch='db_mobilenet_v3_large',
+>>>                           reco_arch=model)
+
+>>> # If your model is a detection model:
+>>> predictor = ocr_predictor(det_arch=model,
+>>>                           reco_arch='crnn_mobilenet_v3_small')
+
+>>> # Get your predictions
+>>> res = predictor(img)
+```
+
+### Layout / table structure models
+
+```python
+>>> from onnxtr.models import from_hub, layout_predictor, table_predictor
+
+>>> model = from_hub('onnxtr/my-model')
+>>> # If your model is a layout model:
+>>> predictor = layout_predictor(arch=model)
+>>> # If your model is a table structure model:
+>>> predictor = table_predictor(arch=model)
+```

config.json

@@ -0,0 +1,21 @@
+{
+  "input_shape": [
+    3,
+    1024,
+    1024
+  ],
+  "mean": [
+    0.798,
+    0.785,
+    0.772
+  ],
+  "std": [
+    0.264,
+    0.2749,
+    0.287
+  ],
+  "url": "https://github.com/felixdittrich92/OnnxTR/releases/download/v0.8.1/tablecenternet-2c8de407.onnx",
+  "url_8_bit": null,
+  "arch": "tablecenternet",
+  "task": "table_structure"
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c8de4071c98e6c8084dbdd5a7968081ad4504f407e20432766b206d663efb70
+size 29372386