001-hello-world

001-hello-world-standalone.ipynb

{"cells": [{"cell_type": "markdown", "id": "miniature-figure", "metadata": {}, "source": "# Hello World\n\nA very basic introduction to OpenVINO that shows how to do inference on a given IR model.\n\nWe use a [MobileNetV3 model](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/mobilenet-v3-small-1.0-224-tf/mobilenet-v3-small-1.0-224-tf.md) from [Open Model Zoo](https://github.com/openvinotoolkit/open_model_zoo/). See the [Tensorflow to OpenVINO Notebook](101-tensorflow-to-openvino) for information on how this OpenVINO IR model was created.\n\n"}, {"id": "dff9e33c", "cell_type": "markdown", "source": "## Preparation\n\nInstall the requirements and download the files that are necessary for running this notebook.\n\n**NOTE:** installation may take a while. It is recommended to restart the Jupyter kernel after installing the packages. Choose *Kernel->Restart Kernel* in Jupyter Notebook or Lab, or *Runtime->Restart runtime* in Google Colab.", "metadata": {}}, {"id": "a340f279", "cell_type": "code", "metadata": {}, "execution_count": null, "source": "# Install or upgrade required Python packages. Install specific versions of some packages to ensure compatibility.\n!pip install openvino-dev opencv-python-headless==4.2.0.32 ipython>7.0 ipywidgets>=7.4", "outputs": []}, {"id": "b511747d", "cell_type": "code", "metadata": {}, "execution_count": null, "source": "# Download image and model files\nimport os\nimport pip\nimport urllib.parse\nimport urllib.request\nfrom pathlib import Path\n\nurls = ['https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/main/notebooks/001-hello-world/imagenet_class_index.json', 'https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/main/notebooks/001-hello-world/v3-small_224_1.0_float.bin', 'https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/main/notebooks/001-hello-world/coco.jpg', 'https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/main/notebooks/001-hello-world/v3-small_224_1.0_float.xml']\n\nnotebook_url = \"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/main\"\n\nfor url in urls:\n    save_path = Path(url).relative_to(fr\"https://raw.githubusercontent.com/openvinotoolkit/openvino_notebooks/main/notebooks/001-hello-world\")\n    os.makedirs(save_path.parent, exist_ok=True)\n    safe_url = urllib.parse.quote(url, safe=\":/\")\n\n    urllib.request.urlretrieve(safe_url, save_path.as_posix())", "outputs": []}, {"cell_type": "markdown", "id": "narrative-officer", "metadata": {}, "source": "## Imports"}, {"cell_type": "code", "execution_count": null, "id": "european-delivery", "metadata": {}, "outputs": [], "source": "import json\n\nimport cv2\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom openvino.inference_engine import IECore"}, {"cell_type": "markdown", "id": "spiritual-bouquet", "metadata": {}, "source": "## Load the network"}, {"cell_type": "code", "execution_count": null, "id": "statewide-growth", "metadata": {}, "outputs": [], "source": "ie = IECore()\nnet = ie.read_network(\n    model=\"v3-small_224_1.0_float.xml\", weights=\"v3-small_224_1.0_float.bin\"\n)\nexec_net = ie.load_network(net, \"CPU\")\n\ninput_key = list(exec_net.input_info)[0]\noutput_key = list(exec_net.outputs.keys())[0]"}, {"cell_type": "markdown", "id": "convertible-literacy", "metadata": {}, "source": "## Load an Image"}, {"cell_type": "code", "execution_count": null, "id": "simplified-accommodation", "metadata": {}, "outputs": [], "source": "# The MobileNet network expects images in RGB format\nimage = cv2.cvtColor(cv2.imread(\"coco.jpg\"), cv2.COLOR_BGR2RGB)\ninput_image = cv2.resize(image, (224, 224))  # resize to MobileNet image shape\ninput_image = np.expand_dims(\n    input_image.transpose(2, 0, 1), 0\n)  # reshape to network input shape\nplt.imshow(image)"}, {"cell_type": "markdown", "id": "warming-platinum", "metadata": {}, "source": "## Do Inference"}, {"cell_type": "code", "execution_count": null, "id": "italic-comment", "metadata": {}, "outputs": [], "source": "result = exec_net.infer(inputs={input_key: input_image})[output_key]\nresult_index = np.argmax(result)"}, {"cell_type": "code", "execution_count": null, "id": "complicated-command", "metadata": {}, "outputs": [], "source": "# Convert the inference result to a class name.\nimagenet_classes = json.loads(open(\"imagenet_class_index.json\").read())\n# The model description states that for this model, class 0 is background,\n# so we add 1 to the network output to get the class name\nimagenet_classes = {\n    int(key) + 1: value for key, value in imagenet_classes.items()\n}\nimagenet_classes[result_index]"}], "metadata": {"kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"}, "language_info": {"codemirror_mode": {"name": "ipython", "version": 3}, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.8"}}, "nbformat": 4, "nbformat_minor": 5}

apt.txt

libpython3.7-dev