Update README for why OpenVINO XAI & known issues (#41)

* Update known issues

* Update why ovxai used

* Address review comment

.markdownlint.yaml

@@ -18,9 +18,15 @@ MD013: false
 # This is not useful for some files such as `CHANGELOG.md`
 MD024: false # Multiple headers with the same content
 
+# no-blanks-blockquote Blank line inside blockquote
+MD028: false
+
 # blanks-around-fences - Fenced code blocks should be surrounded by blank lines
 MD031: false
 
+# blanks-around-lists Lists should be surrounded by blank lines
+MD032: false
+
 # I find it necessary to use '<br/>' to force line breaks.
 MD033: false # Inline HTML
 

CHANGELOG.md

@@ -95,7 +95,6 @@
 
 ### Known Issues
 
-* OpenVINO IR branch insertion not working for models converted directly from torch models in https://github.com/openvinotoolkit/openvino_xai/issues/26
 * Runtime error from ONNX / OpenVINO IR models while conversion or inference for XAI in https://github.com/openvinotoolkit/openvino_xai/issues/29
 * Models not supported by white box XAI methods in https://github.com/openvinotoolkit/openvino_xai/issues/30
 

README.md

@@ -30,6 +30,23 @@ Given **OpenVINO** models and input images, **OpenVINO XAI** generates **salienc
 which highlights regions of the interest in the inputs from the models' perspective
 to help users understand the reason why the complex AI models output such responses.
 
+Using this package, you can augment the model analysis & explanation feature
+on top of the existing OpenVINO inference pipeline with a few lines of code.
+
+```python
+import openvino_xai as xai
+
+explainer = xai.Explainer(model=ov_model, task=xai.Task.CLASSIFICATION)
+
+# Existing inference pipeline
+for i, image in enumerate(images):
+    labels = infer(model=ov_model, image=image)
+
+    # Model analysis
+    explanation = explainer(data=image, targets=labels)
+    explanation.save(dir_path="./xai", name=str(i))
+```
+
 ---
 
 ## Features
@@ -64,10 +81,13 @@ Most of CNNs and Transformer models from [Pytorch Image Models (timm)](https://g
 
 Please refer to the following known issues for unsupported models and reasons.
 
-* [OpenVINO IR branch insertion not working for models converted directly from torch models with OVC (#26)](https://github.com/openvinotoolkit/openvino_xai/issues/26)
 * [Runtime error from ONNX / OpenVINO IR models while conversion or inference for XAI (#29)](https://github.com/openvinotoolkit/openvino_xai/issues/29)
 * [Models not supported by white box XAI methods (#30)](https://github.com/openvinotoolkit/openvino_xai/issues/30)
 
+> **_WARNING:_**  OpenVINO XAI is fully validated on OpenVINO 2024.2.0. Following issue might be observed if older version of OpenVINO is used.
+> * [OpenVINO IR branch insertion not working for models converted directly from torch models with OVC (#26)](https://github.com/openvinotoolkit/openvino_xai/issues/26)
+> A simple workaround is to convert Torch models to ONNX models and then convert to OpenVINO models to feed to OpenVINO XAI. Please refer to [the code example](openvino_xai/utils/model_export.py).
+
 > **_NOTE:_**  GenAI / LLMs would be also supported incrementally in the upcoming releases.
 
 ---

tests/intg/test_classification.py

@@ -1,7 +1,7 @@
 # Copyright (C) 2023-2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-import subprocess
+import subprocess  # nosec B404 (not a part of product)
 from pathlib import Path
 
 import cv2

tests/intg/test_detection.py

@@ -1,7 +1,7 @@
 # Copyright (C) 2023-2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-import subprocess
+import subprocess  # nosec B404 (not a part of product)
 from pathlib import Path
 
 import addict