Remove config dependency from OpenVINOInferencer (openvinotoolkit#939)

* Use case Dobot - WIP commit (openvinotoolkit#884) * WIP commit * training via config file and robot control * 2 notebooks robot control * Removed utils directory from notebooks/500_use_cases * Removed utils directory from `notebooks/500_use_cases` (openvinotoolkit#911) Removed utils directory from notebooks/500_use_cases * Download the dataset and the api from anomalib assets * adding readme file * adding instructions * adding instructions * adding instructions * adding instructions * adding instructions * adding instructions * adding instructions * adding instructions * adding instructions * adding instructions * Update README.md * Model training is done via API now * Metadata change * Metadata change * Metadata change * Metadata change * Metadata change * Metadata change * Metadata change * update docstring * Address pre-commit * Address pre-commit issues * Address pre-commit issues * Fixed the bugs spotted by Paula * Fix export tests * Address pre-commit issues * Update test_export.py * Update base.txt * Revert metadata rename in changelog * Addressed reviewer comments * remove config from openvino in notebooks * remove config from openvino in notebooks * add unreleased section to changelog * Address tox output * Change the directory path of dobot * Update CHANGELOG.md * Revert the figure back in notebook * Revert padim configs * Fix getting started jupyter notebook that failed * Fix metadata path --------- Co-authored-by: Paula Ramos <[email protected]>
jpcbertoldo · Mar 10, 2023 · f023a83 · f023a83
1 parent 6834e5b
commit f023a83
Show file tree

Hide file tree

Showing 23 changed files with 239 additions and 519 deletions.
diff --git a/.gitignore b/.gitignore
@@ -5,6 +5,10 @@ datasets
 results
 !anomalib/core/results
 
+# Jupyter Notebooks
+notebooks/500_use_cases/501_dobot/
+!notebooks/500_use_cases/501_dobot/*.ipynb
+
 # VENV
 .python-version
 .anomalib

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,6 +10,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ### Changed
 
+- Remove `config` flag from `OpenVINOInferencer` (<https://github.com/openvinotoolkit/anomalib/pull/939>)
+
 ### Deprecated
 
 ###  Fixed

diff --git a/README.md b/README.md
@@ -198,12 +198,12 @@ Example OpenVINO Inference:
 python tools/inference/openvino_inference.py \
     --config anomalib/models/padim/config.yaml \
     --weights results/padim/mvtec/bottle/openvino/openvino_model.bin \
-    --meta_data results/padim/mvtec/bottle/openvino/meta_data.json \
+    --meta_data results/padim/mvtec/bottle/openvino/metadata.json \
     --input datasets/MVTec/bottle/test/broken_large/000.png \
     --output results/padim/mvtec/bottle/images
 ```
 
-> Ensure that you provide path to `meta_data.json` if you want the normalization to be applied correctly.
+> Ensure that you provide path to `metadata.json` if you want the normalization to be applied correctly.
 
 You can also use Gradio Inference to interact with the trained models using a UI. Refer to our [guide](https://openvinotoolkit.github.io/anomalib/guides/inference.html#gradio-inference) for more details.
 

diff --git a/docs/source/tutorials/inference.rst b/docs/source/tutorials/inference.rst
@@ -52,17 +52,17 @@ To run OpenVINO inference, first make sure that your model has been exported to
 +-----------+----------+--------------------------------------------------------------------------------------+
 | save_data | False    | Path to which the output images should be saved. Leave empty for live visualization. |
 +-----------+----------+--------------------------------------------------------------------------------------+
-| meta_data | True     | Path to the JSON file containing the model's meta data (e.g. normalization           |
+| metadata | True     | Path to the JSON file containing the model's meta data (e.g. normalization           |
 |           |          | parameters and anomaly score threshold).                                             |
 +-----------+----------+--------------------------------------------------------------------------------------+
 | device    | False    | Device on which OpenVINO will perform the computations (``CPU``, ``GPU`` or ``VPU``) |
 +-----------+----------+--------------------------------------------------------------------------------------+
 
-For correct inference results, the ``meta_data`` argument should be specified and point to the ``meta_data.json`` file that was generated when exporting the OpenVINO IR model. The file is stored in the same folder as the ``.xml`` and ``.bin`` files of the model.
+For correct inference results, the ``metadata`` argument should be specified and point to the ``metadata.json`` file that was generated when exporting the OpenVINO IR model. The file is stored in the same folder as the ``.xml`` and ``.bin`` files of the model.
 
 As an example, OpenVINO inference can be triggered by the following command:
 
-``python tools/inference/openvino.py --config padim.yaml --weights results/openvino/model.xml --input image.png --meta_data results/openvino/meta_data.json``
+``python tools/inference/openvino.py --config padim.yaml --weights results/openvino/model.xml --input image.png --metadata results/openvino/metadata.json``
 
 Similar to PyTorch inference, the visualization results will be displayed on the screen, and optionally saved to the file system location specified by the ``save_data`` parameter.
 
@@ -80,15 +80,15 @@ The gradio inference is supported for both PyTorch and OpenVINO models.
 +-----------+----------+------------------------------------------------------------------+
 | weights   | True     | Path to the OpenVINO IR model file (either ``.xml`` or ``.bin``) |
 +-----------+----------+------------------------------------------------------------------+
-| meta_data | False    | Path to the JSON file containing the model's meta data.          |
+| metadata | False    | Path to the JSON file containing the model's meta data.          |
 |           |          | This is needed only for OpenVINO model.                          |
 +-----------+----------+------------------------------------------------------------------+
 | threshold | False    | Threshold value used for identifying anomalies. Range 1-100.     |
 +-----------+----------+------------------------------------------------------------------+
 | share     | False    | Share Gradio `share_url`                                         |
 +-----------+----------+------------------------------------------------------------------+
 
-To use gradio with OpenVINO model, first make sure that your model has been exported to the OpenVINO IR format and ensure that the `meta_data` argument points to the ``meta_data.json`` file that was generated when exporting the OpenVINO IR model. The file is stored in the same folder as the ``.xml`` and ``.bin`` files of the model.
+To use gradio with OpenVINO model, first make sure that your model has been exported to the OpenVINO IR format and ensure that the `metadata` argument points to the ``metadata.json`` file that was generated when exporting the OpenVINO IR model. The file is stored in the same folder as the ``.xml`` and ``.bin`` files of the model.
 
 As an example, PyTorch model can be used by the following command:
 
@@ -105,4 +105,4 @@ Similarly, you can use OpenVINO model by the following command:
     python python tools/inference/gradio_inference.py \
         --config ./anomalib/models/padim/config.yaml \
         --weights ./results/padim/mvtec/bottle/openvino/openvino_model.onnx \
-        --meta_data ./results/padim/mvtec/bottle/openvino/meta_data.json
+        --metadata ./results/padim/mvtec/bottle/openvino/metadata.json
diff --git a/notebooks/000_getting_started/001_getting_started.ipynb b/notebooks/000_getting_started/001_getting_started.ipynb
@@ -434,7 +434,7 @@
    ],
    "source": [
     "openvino_model_path = output_path / \"openvino\" / \"model.bin\"\n",
-    "metadata_path = output_path / \"openvino\" / \"meta_data.json\"\n",
+    "metadata_path = output_path / \"openvino\" / \"metadata.json\"\n",
     "print(openvino_model_path.exists(), metadata_path.exists())"
    ]
   },
@@ -445,9 +445,8 @@
    "outputs": [],
    "source": [
     "inferencer = OpenVINOInferencer(\n",
-    "    config=CONFIG_PATH,  # Pass the config file to the inferencer.\n",
     "    path=openvino_model_path,  # Path to the OpenVINO IR model.\n",
-    "    meta_data_path=metadata_path,  # Path to the metadata file.\n",
+    "    metadata_path=metadata_path,  # Path to the metadata file.\n",
     "    device=\"CPU\",  # We would like to run it on an Intel CPU.\n",
     ")"
    ]

diff --git a/...ooks/500_use_cases/501_dobot/501a_Dataset_creation_and_Inference_with_a_robotic_arm.ipynb b/...ooks/500_use_cases/501_dobot/501a_Dataset_creation_and_Inference_with_a_robotic_arm.ipynb
@@ -67,7 +67,6 @@
     "# importing required libraries\n",
     "import cv2  # OpenCV library\n",
     "import matplotlib.pyplot as plt\n",
-    "\n",
     "from anomalib.deploy import OpenVINOInferencer"
    ]
   },
@@ -248,7 +247,6 @@
     "# If acquisition is False this notebook will work in inference mode\n",
     "if acquisition is False:\n",
     "    # If you are running inference check where the OpenVINO model is stored\n",
-    "    CONFIG_PATH = notebook_path / \"cubes_config.yaml\"\n",
     "    openvino_model_path = notebook_path / \"openvino\" / \"model.bin\"\n",
     "    metadata_path = notebook_path / \"openvino\" / \"meta_data.json\"\n",
     "    print(\"OpenVINO model exist: \", openvino_model_path.exists())\n",
@@ -257,9 +255,8 @@
     "    print(\"Metadata path: \", metadata_path)\n",
     "\n",
     "    inferencer = OpenVINOInferencer(\n",
-    "        config=CONFIG_PATH,  # Pass the config file to the inferencer.\n",
     "        path=openvino_model_path,  # Path to the OpenVINO IR model.\n",
-    "        meta_data_path=metadata_path,  # Path to the metadata file.\n",
+    "        metadata_path=metadata_path,  # Path to the metadata file.\n",
     "        device=\"CPU\",  # We would like to run it on an Intel CPU.\n",
     "    )\n",
     "\n",
@@ -558,19 +555,11 @@
     "        dType.SetPTPCmdEx(api, 0, Calibration_X, Calibration_Y, Calibration_Z, 0, 1)\n",
     "        cam_stream.stop()  # stop the webcam stream"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5b1bb666",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "project_anomalib",
+   "display_name": "anomalib",
    "language": "python",
    "name": "python3"
   },
@@ -584,11 +573,11 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.16"
+   "version": "3.8.13"
   },
   "vscode": {
    "interpreter": {
-    "hash": "18f8999b3d132acda9ed72c7f0f7e54d3c533278cffbadac58c30769cf876377"
+    "hash": "ae223df28f60859a2f400fae8b3a1034248e0a469f5599fd9a89c32908ed7a84"
    }
   }
  },