-
Notifications
You must be signed in to change notification settings - Fork 58
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #889 from sony/quickstart-table
Update README.md
- Loading branch information
Showing
2 changed files
with
376 additions
and
4 deletions.
There are no files selected for viewing
214 changes: 214 additions & 0 deletions
214
tutorials/notebooks/example_quick_start_torchvision.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,214 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "c9e7b10d2bfe67d4", | ||
| "metadata": { | ||
| "collapsed": false, | ||
| "id": "c9e7b10d2bfe67d4" | ||
| }, | ||
| "source": [ | ||
| "# Quick Start\n", | ||
| "\n", | ||
| "[Run this tutorial in Google Colab](https://colab.research.google.com/github/sony/model_optimization/blob/main/tutorials/notebooks/example_quick_start_torchvision.ipynb)" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "9bc664bf", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Overview\n", | ||
| "This tutorial shows how to use \"quick-start\" with a pre-trained model from the torchvision library.\n", | ||
| "\n", | ||
| "The following steps will be covered:\n", | ||
| "\n", | ||
| "* **Setup the environment**: install MCT and add tutorials to PYTHONPATH\n", | ||
| "* **Download and organize the imagenet dataset**\n", | ||
| "* **Run quick_start on your model**\n", | ||
| "\n", | ||
| "**Note**: The following code will run faster on a GPU." | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "d0e81b09e6d30873", | ||
| "metadata": { | ||
| "collapsed": false, | ||
| "id": "d0e81b09e6d30873" | ||
| }, | ||
| "source": [ | ||
| "## Setup\n", | ||
| "\n", | ||
| "Install and import relevant packages" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "eda6ab0d8f0b6b56", | ||
| "metadata": { | ||
| "collapsed": false, | ||
| "id": "eda6ab0d8f0b6b56" | ||
| }, | ||
| "source": [ | ||
| "In order to use quick-start you'll need the [MCT tutorial folder](https://github.com/sony/model_optimization/tree/main/tutorials), so we'll clone the MCT repository to a local folder and use that code.\n", | ||
| "\n", | ||
| " **It's important to note that we use the most up-to-date MCT code available.**" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "ca9a743c0e7ba067", | ||
| "metadata": { | ||
| "colab": { | ||
| "base_uri": "https://localhost:8080/" | ||
| }, | ||
| "id": "ca9a743c0e7ba067", | ||
| "outputId": "10c7246b-8b31-4c44-9a45-04d4d3a2958b" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "!git clone https://github.com/sony/model_optimization.git local_mct\n", | ||
| "!pip install -r ./local_mct/requirements.txt" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "PfJ3_AyieBL0", | ||
| "metadata": { | ||
| "id": "PfJ3_AyieBL0" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import os\n", | ||
| "os.environ['PYTHONPATH'] = './local_mct/'" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "ufTwrlH-eCyB", | ||
| "metadata": { | ||
| "id": "ufTwrlH-eCyB" | ||
| }, | ||
| "source": [ | ||
| "## Dataset\n", | ||
| "Download the imagenet validation dataset.\n", | ||
| "\n", | ||
| "Use torchvision.datasets.ImageNet to create the dataset in the correct structure.\n", | ||
| "\n", | ||
| "**Note**: We use validation for time convinience since the training split is too big. Typically, the validation samples should only be used for testing." | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "cj6WQGrLvkvx", | ||
| "metadata": { | ||
| "colab": { | ||
| "base_uri": "https://localhost:8080/" | ||
| }, | ||
| "id": "cj6WQGrLvkvx", | ||
| "outputId": "46efb6a0-abe3-48d9-ce89-6890a566e6de" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "!mkdir imagenet\n", | ||
| "!wget https://image-net.org/data/ILSVRC/2012/ILSVRC2012_devkit_t12.tar.gz\n", | ||
| "!mv ILSVRC2012_devkit_t12.tar.gz imagenet/\n", | ||
| "!wget https://image-net.org/data/ILSVRC/2012/ILSVRC2012_img_val.tar\n", | ||
| "!mv ILSVRC2012_img_val.tar imagenet/" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 4, | ||
| "id": "coxDAP4Av3ol", | ||
| "metadata": { | ||
| "id": "coxDAP4Av3ol" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import torchvision\n", | ||
| "ds = torchvision.datasets.ImageNet(root='./imagenet', split='val')" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "gY2UsnzOfjtk", | ||
| "metadata": { | ||
| "id": "gY2UsnzOfjtk" | ||
| }, | ||
| "source": [ | ||
| "## Run Quick Start script on our model of choice\n", | ||
| "\n", | ||
| "Here we set the model name, model library, validation dataset path, and representative datasets path.\n", | ||
| " \n", | ||
| "The remaining arguments are left with their default settings. Please verify that the dataset paths are configured correctly." | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "ZJ8CR1FQRwg2", | ||
| "metadata": { | ||
| "colab": { | ||
| "base_uri": "https://localhost:8080/" | ||
| }, | ||
| "id": "ZJ8CR1FQRwg2", | ||
| "outputId": "607f95e7-8c80-408f-ebe8-ace70f999e3e" | ||
| }, | ||
| "outputs": [], | ||
| "source": [ | ||
| "!python ./local_mct/tutorials/quick_start/main.py --model_name mobilenet_v2 --model_library torchvision --validation_dataset_folder ./imagenet/val --representative_dataset_folder ./imagenet/val" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "id": "d5d80935", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "\n", | ||
| "Copyright 2024 Sony Semiconductor Israel, Inc. All rights reserved.\n", | ||
| "\n", | ||
| "Licensed under the Apache License, Version 2.0 (the \"License\");\n", | ||
| "you may not use this file except in compliance with the License.\n", | ||
| "You may obtain a copy of the License at\n", | ||
| "\n", | ||
| " http://www.apache.org/licenses/LICENSE-2.0\n", | ||
| "\n", | ||
| "Unless required by applicable law or agreed to in writing, software\n", | ||
| "distributed under the License is distributed on an \"AS IS\" BASIS,\n", | ||
| "WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", | ||
| "See the License for the specific language governing permissions and\n", | ||
| "limitations under the License.\n" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "accelerator": "GPU", | ||
| "colab": { | ||
| "gpuType": "T4", | ||
| "provenance": [] | ||
| }, | ||
| "kernelspec": { | ||
| "display_name": "Python 3", | ||
| "name": "python3" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 2 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython2", | ||
| "version": "2.7.6" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 5 | ||
| } |
Oops, something went wrong.