Created using Colab

jonbaer · May 15, 2024 · c6c1c66 · c6c1c66
1 parent 376bbad
commit c6c1c66
Showing 1 changed file with 148 additions and 0 deletions.
diff --git a/quick_start_google_edge.ipynb b/quick_start_google_edge.ipynb
@@ -0,0 +1,148 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Earrbj1HNaVk"
+      },
+      "source": [
+        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/google-ai-edge/model-explorer/blob/main/example_colabs/quick_start.ipynb)\n",
+        "\n",
+        "# Google AI Edge Model Explorer\n",
+        "A visualization tool that lets you analyze ML models and graphs, accelerating deployment to on-device targets. [Learn more](https://ai.google.dev/edge/model-explorer).\n",
+        "\n",
+        "**Key Features**\n",
+        "\n",
+        "* Visualize large models effortlessly\n",
+        "* Find model conversion issues\n",
+        "* Identify optimization targets\n",
+        "* Easy to use intuitive UI\n",
+        "\n",
+        "Follow the [installation instructions](https://github.com/google-ai-edge/model-explorer/wiki/5.-Run-in-Colab-Notebook) to add it to your own Colab.\n",
+        "\n",
+        "Want to run Model Explorer locally? [Get Started here](https://github.com/google-ai-edge/model-explorer/wiki/1.-Installation)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "vCM_sxQsg2nj"
+      },
+      "source": [
+        "# Download a copy of the EfficientDet TFLite model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "SmUNdu2jhU1z"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import tempfile\n",
+        "import urllib.request\n",
+        "import torch\n",
+        "import torchvision\n",
+        "\n",
+        "tmp_path = tempfile.mkdtemp()\n",
+        "model_path = os.path.join(tmp_path, 'model.tflite')\n",
+        "urllib.request.urlretrieve(\"https://storage.googleapis.com/tfweb/model-graph-vis-v2-test-models/efficientdet.tflite\", model_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "nSHa2LHCg7Gz"
+      },
+      "source": [
+        "# Install Model Explorer using pip"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XqnjhEVqkSvU"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install ai-edge-model-explorer\n",
+        "\n",
+        "# Faster installation by skipping deps that are included in colab runtime:\n",
+        "# !pip install --no-deps ai-edge-model-explorer-adapter ai-edge-model-explorer"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tNzvaoFHhBJR"
+      },
+      "source": [
+        "# Visualize the downloaded EfficientDet model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "_qycf3tbmP_S"
+      },
+      "outputs": [],
+      "source": [
+        "import model_explorer\n",
+        "\n",
+        "model_explorer.visualize(model_path)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Q3aMYkE6HMPM"
+      },
+      "source": [
+        "# Visualize a PyTorch model\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "sZJkEgdsHSH9"
+      },
+      "outputs": [],
+      "source": [
+        "# Get mobilnet v2 pytorch model as an example.\n",
+        "model = torchvision.models.mobilenet_v2().eval()\n",
+        "inputs = (torch.rand([1, 3, 224, 224]),)\n",
+        "ep = torch.export.export(model, inputs)\n",
+        "\n",
+        "# Visualize\n",
+        "model_explorer.visualize_pytorch('mobilenet', exported_program=ep)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "collapsed_sections": [
+        "vCM_sxQsg2nj",
+        "nSHa2LHCg7Gz",
+        "tNzvaoFHhBJR",
+        "Q3aMYkE6HMPM"
+      ],
+      "private_outputs": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}