[BERT-NER] Document model support (#6238)

* added docs

* up to date with release branch

* delete print

docs/MO_DG/prepare_model/convert_model/Convert_Model_From_PyTorch.md

@@ -26,6 +26,7 @@ It is not a full list of models that can be converted to ONNX\* and to IR.
 * QuartzNet topologies from [NeMo project](https://github.com/NVIDIA/NeMo) can be converted using [Convert PyTorch\* QuartzNet to the IR](pytorch_specific/Convert_QuartzNet.md) instruction.
 * YOLACT topology can be converted using [Convert PyTorch\* YOLACT to the IR](pytorch_specific/Convert_YOLACT.md) instruction.
 * [RCAN](https://github.com/yulunzhang/RCAN) topologies can be converted using [Convert PyTorch\* RCAN to the IR](pytorch_specific/Convert_RCAN.md) instruction.
+* [BERT_NER](https://github.com/kamalkraj/BERT-NER) can be converted using [Convert PyTorch* BERT-NER to the IR](pytorch_specific/Convert_Bert_ner.md) instruction.
 
 ## Export PyTorch\* Model to ONNX\* Format <a name="export-to-onnx"></a>
 

docs/MO_DG/prepare_model/convert_model/pytorch_specific/Convert_Bert_ner.md

@@ -0,0 +1,55 @@
+# Convert PyTorch* BERT-NER to the Intermediate Representation {#openvino_docs_MO_DG_prepare_model_convert_model_pytorch_specific_Convert_Bert_ner}
+
+## Download and Convert the Model to ONNX*
+
+To download a pre-trained model or train the model yourself, refer
+to the [instruction](https://github.com/kamalkraj/BERT-NER/blob/dev/README.md) in the
+BERT-NER model repository. The model with config files is stored in the `out_base` directory.
+
+To convert the model to ONNX* format, create and run the script with the following content in the root
+directory of the model repository. If you download the pre-trained model, you need
+to download [`bert.py`](https://github.com/kamalkraj/BERT-NER/blob/dev/bert.py) to run the script.
+The instruction was tested with the repository hash commit `e5be564156f194f1becb0d82aeaf6e762d9eb9ed`.
+
+```python
+import torch
+
+from bert import Ner
+
+ner = Ner("out_base")
+
+input_ids, input_mask, segment_ids, valid_positions = ner.preprocess('Steve went to Paris')
+input_ids = torch.tensor([input_ids], dtype=torch.long, device=ner.device)
+input_mask = torch.tensor([input_mask], dtype=torch.long, device=ner.device)
+segment_ids = torch.tensor([segment_ids], dtype=torch.long, device=ner.device)
+valid_ids = torch.tensor([valid_positions], dtype=torch.long, device=ner.device)
+
+ner_model, tknizr, model_config = ner.load_model("out_base")
+
+with torch.no_grad():
+    logits = ner_model(input_ids, segment_ids, input_mask, valid_ids)
+torch.onnx.export(ner_model,
+                  (input_ids, segment_ids, input_mask, valid_ids),
+                  "bert-ner.onnx",
+                  input_names=['input_ids', 'segment_ids', 'input_mask', 'valid_ids'],
+                  output_names=['output'],
+                  dynamic_axes={
+                      "input_ids": {0: "batch_size"},
+                      "segment_ids": {0: "batch_size"},
+                      "input_mask": {0: "batch_size"},
+                      "valid_ids": {0: "batch_size"},
+                      "output": {0: "output"}
+                  },
+                  opset_version=11,
+                  )
+```
+
+The script generates ONNX* model file `bert-ner.onnx`.
+
+## Convert ONNX* BERT-NER model to IR
+
+```bash
+python mo.py --input_model bert-ner.onnx --input "input_mask[1 128],segment_ids[1 128],input_ids[1 128]"
+```
+
+where `1` is `batch_size` and `128` is `sequence_length`.

docs/doxygen/ie_docs.xml

@@ -61,6 +61,7 @@ limitations under the License.
                             <tab type="user" title="Convert PyTorch* YOLACT Model" url="@ref openvino_docs_MO_DG_prepare_model_convert_model_pytorch_specific_Convert_YOLACT"/>
                             <tab type="user" title="Convert PyTorch* F3Net Model" url="@ref openvino_docs_MO_DG_prepare_model_convert_model_pytorch_specific_Convert_F3Net"/>
                             <tab type="user" title="Convert PyTorch* RCAN Model" url="@ref openvino_docs_MO_DG_prepare_model_convert_model_pytorch_specific_Convert_RCAN">
+                            <tab type="user" title="Convert PyTorch* BERT-NER Model" url="@ref openvino_docs_MO_DG_prepare_model_convert_model_pytorch_specific_Convert_Bert_ner"/>
                             </tab>
                         </tab>
                         <tab type="user" title="Model Optimizations Techniques" url="@ref openvino_docs_MO_DG_prepare_model_Model_Optimization_Techniques"/>