From d3a69d09d63da6a4e7de93f83b09e4cb329f4936 Mon Sep 17 00:00:00 2001 From: Andrea Ovalle <74880762+ovalle15@users.noreply.github.com> Date: Fri, 28 Oct 2022 09:34:32 -0400 Subject: [PATCH] Update project setup --- .../project_configuration/project_setup.ipynb | 599 ++++++++++++------ 1 file changed, 394 insertions(+), 205 deletions(-) diff --git a/examples/project_configuration/project_setup.ipynb b/examples/project_configuration/project_setup.ipynb index 6914e4593..52f394107 100644 --- a/examples/project_configuration/project_setup.ipynb +++ b/examples/project_configuration/project_setup.ipynb @@ -1,217 +1,406 @@ { - "cells": [ - { - "cell_type": "markdown", - "id": "db768cda", - "metadata": {}, - "source": [ - "\n", - " \n", - "" - ] - }, - { - "cell_type": "markdown", - "id": "cb5611d0", - "metadata": {}, - "source": [ - "\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "" - ] - }, - { - "cell_type": "markdown", - "id": "boxed-football", - "metadata": {}, - "source": [ - "# Project Setup\n", - "* This notebok describes how to create and configure a project\n", - "* This is the same as creating a new project in the editor and going through all of the steps." - ] - }, - { - "cell_type": "markdown", - "id": "thousand-difference", - "metadata": {}, - "source": [ - "* When a user creates a project with client.create_project() the project is not ready for labeling.\n", - " * An ontology must be set\n", - " * datasets must be attached" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "id": "contemporary-banking", - "metadata": {}, - "outputs": [], - "source": [ - "!pip install labelbox" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "id": "ordered-notice", - "metadata": {}, - "outputs": [], - "source": [ - "from labelbox import Client, Project, Tool, OntologyBuilder\n", - "from labelbox.schema.media_type import MediaType" - ] - }, - { - "cell_type": "markdown", - "id": "2c66dbf3", - "metadata": {}, - "source": [ - "# API Key and Client\n", - "Provide a valid api key below in order to properly connect to the Labelbox Client." - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "royal-algeria", - "metadata": {}, - "outputs": [], - "source": [ - "# Add your api key\n", - "API_KEY = None\n", - "client = Client(api_key=API_KEY)" - ] - }, - { - "cell_type": "markdown", - "id": "least-stone", - "metadata": {}, - "source": [ - "### Create Dataset\n", - "* Create dataset and attach data\n", - "* More details on attaching data can be found [here](https://github.com/Labelbox/labelbox-python/blob/develop/examples/basics/data_rows.ipynb)" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "0c195add", - "metadata": {}, - "outputs": [], - "source": [ - "dataset = client.create_dataset(name=\"my_new_dataset\")\n", - "# Add data_rows since this is a new dataset (see basics/data_rows.ipynb for more information on this)\n", - "test_img_url = \"https://raw.githubusercontent.com/Labelbox/labelbox-python/develop/examples/assets/2560px-Kitano_Street_Kobe01s5s4110.jpg\"\n", - "dataset.create_data_row(row_data=test_img_url)" - ] - }, - { - "cell_type": "markdown", - "id": "e4f8b7f7", - "metadata": {}, - "source": [ - "### Create Or Select an Ontology\n", - "* Optionally create an ontology or select from an existing one.\n", - "* More details on ontology management can be found [here](https://github.com/Labelbox/labelbox-python/blob/develop/examples/basics/ontologies.ipynb)\n", - " " - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "id": "a9e4738c", - "metadata": {}, - "outputs": [], - "source": [ - "# Create\n", - "ontology_builder = OntologyBuilder(\n", - " tools=[Tool(name=\"cat\", tool=Tool.Type.BBOX)])\n", - "ontology = client.create_ontology(\"project-setup-demo-ontology\",\n", - " ontology_builder.asdict())\n", - "# Select existing ontology\n", - "#ontology = client.get_ontology(\"\")\n", - "#ontology = existing_project.ontology()" - ] - }, - { - "cell_type": "markdown", - "id": "limiting-bleeding", - "metadata": {}, - "source": [ - "### Create Project and Setup the Editor\n", - "* Setting up a project will add an ontology and will enable labeling to begin\n", - "* Attaching dataset(s) will add all data_rows belonging to the dataset to the queue." - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "reserved-vietnam", - "metadata": {}, - "outputs": [], - "source": [ - "project = client.create_project(name=\"my_new_project\", media_type=MediaType.Image)\n", - "project.setup_editor(ontology)\n", - "project.datasets.connect(dataset)" - ] + "cells": [ + { + "cell_type": "markdown", + "id": "db768cda", + "metadata": { + "id": "db768cda" + }, + "source": [ + "\n", + " \n", + "" + ] + }, + { + "cell_type": "markdown", + "id": "cb5611d0", + "metadata": { + "id": "cb5611d0" + }, + "source": [ + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "" + ] + }, + { + "cell_type": "markdown", + "id": "boxed-football", + "metadata": { + "id": "boxed-football" + }, + "source": [ + "# Project Setup\n", + "* This notebok describes how to create and configure a project\n", + "* This is the same as creating a new project in the editor and going through all of the steps." + ] + }, + { + "cell_type": "markdown", + "id": "thousand-difference", + "metadata": { + "id": "thousand-difference" + }, + "source": [ + "* When a user creates a project with client.create_project() the project is not ready for labeling.\n", + " * An ontology must be set\n", + " * Datasets/Batchh must be attached" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "contemporary-banking", + "metadata": { + "id": "contemporary-banking" + }, + "outputs": [], + "source": [ + "!pip install labelbox[data]" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "ordered-notice", + "metadata": { + "id": "ordered-notice" + }, + "outputs": [], + "source": [ + "from labelbox import Client, Project, Tool, OntologyBuilder\n", + "from labelbox.schema.media_type import MediaType\n", + "from labelbox.schema.queue_mode import QueueMode\n", + "import uuid" + ] + }, + { + "cell_type": "markdown", + "id": "2c66dbf3", + "metadata": { + "id": "2c66dbf3" + }, + "source": [ + "# API Key and Client\n", + "Provide a valid api key below in order to properly connect to the Labelbox Client." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "royal-algeria", + "metadata": { + "id": "royal-algeria" + }, + "outputs": [], + "source": [ + "# Add your api key\n", + "API_KEY=None\n", + "client = Client(api_key=API_KEY)" + ] + }, + { + "cell_type": "markdown", + "id": "least-stone", + "metadata": { + "id": "least-stone" + }, + "source": [ + "### Create Dataset\n", + "* Create dataset and attach data\n", + "* More details on attaching data can be found [here](https://github.com/Labelbox/labelbox-python/blob/develop/examples/basics/data_rows.ipynb)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "0c195add", + "metadata": { + "id": "0c195add", + "colab": { + "base_uri": "https://localhost:8080/" }, + "outputId": "de924e2b-f996-42b5-e02a-337c5662eaa4" + }, + "outputs": [ { - "cell_type": "markdown", - "id": "afraid-trademark", - "metadata": {}, - "source": [ - "### Review" - ] + "output_type": "stream", + "name": "stdout", + "text": [ + "ERRORS: None\n", + "RESULT URL: https://storage.labelbox.com/cl3ahv73w1891087qbwzs3edd%2Fdata-row-imports-results%2Fcl9sj9crk0zf307yo0mnm17y4_cl9sj9e1u50gm07upd3xj7vyx.json?Expires=1667050292662&KeyName=labelbox-assets-key-3&Signature=JW912R-7wveaHGyhkdKIBRKEtVw\n" + ] + } + ], + "source": [ + "dataset = client.create_dataset(name=\"project_setup_demo\")\n", + "## Example image\n", + "uploads = []\n", + "# Generate data rows\n", + "for i in range(1,9):\n", + " uploads.append({\n", + " 'row_data': f\"https://storage.googleapis.com/labelbox-datasets/People_Clothing_Segmentation/jpeg_images/IMAGES/img_000{i}.jpeg\",\n", + " \"global_key\": f\"ID-{ uuid.uuid1()}\"\n", + " })\n", + "data_rows = dataset.create_data_rows(uploads)\n", + "data_rows.wait_till_done()\n", + "print(\"ERRORS: \" , data_rows.errors)\n", + "print(\"RESULT URL: \", data_rows.result_url)" + ] + }, + { + "cell_type": "markdown", + "id": "e4f8b7f7", + "metadata": { + "id": "e4f8b7f7" + }, + "source": [ + "### Create Or Select an Ontology\n", + "* Optionally create an ontology or select from an existing one.\n", + "* More details on ontology management can be found [here](https://github.com/Labelbox/labelbox-python/blob/develop/examples/basics/ontologies.ipynb)\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "a9e4738c", + "metadata": { + "id": "a9e4738c" + }, + "outputs": [], + "source": [ + "# Create\n", + "ontology_builder = OntologyBuilder(\n", + " tools=[Tool(name=\"cat\", tool=Tool.Type.BBOX)])\n", + "ontology = client.create_ontology(\"project-setup-demo-ontology\",\n", + " ontology_builder.asdict())\n", + "# Select existing ontology\n", + "#ontology = client.get_ontology(\"\")\n", + "#ontology = existing_project.ontology()" + ] + }, + { + "cell_type": "markdown", + "id": "limiting-bleeding", + "metadata": { + "id": "limiting-bleeding" + }, + "source": [ + "### Create Project and Setup the Editor\n", + "* Setting up a project will add an ontology and will enable labeling to begin\n", + "* Attaching dataset(s) will add all data_rows belonging to the dataset to the queue.\n", + "* Creating batches will add data rows exported from a dataset" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "reserved-vietnam", + "metadata": { + "id": "reserved-vietnam" + }, + "outputs": [], + "source": [ + "batch_project = client.create_project(name=\"batch-test-project\", \n", + " media_type=MediaType.Image,\n", + " # Setup quality settings (Benchmarks)\n", + " auto_audit_percentage=1,\n", + " auto_audit_number_of_labels=1,\n", + " queue_mode=QueueMode.Batch)\n", + "\n", + "\n", + "dataset_project = client.create_project(name=\"dataset-test-project\",\n", + " description=\"a description\",\n", + " media_type=MediaType.Image,\n", + " ## Setup quality settings (Consensus)\n", + " auto_audit_percentage=0.1,\n", + " auto_audit_number_of_labels=3,\n", + " queue_mode=QueueMode.Dataset)\n", + "\n", + "batch_project.setup_editor(ontology)\n", + "dataset_project.setup_editor(ontology)\n" + ] + }, + { + "cell_type": "markdown", + "source": [ + "# Add data to your projects " + ], + "metadata": { + "id": "yLPMPtv6-zPU" + }, + "id": "yLPMPtv6-zPU" + }, + { + "cell_type": "code", + "source": [ + "\n", + "####### Connect your dataset \n", + "# Dataset projects do not support batches\n", + "\n", + "dataset_project.datasets.connect(dataset)\n", + "\n", + "######## Create batches \n", + "# Batch projects do not support datasets\n", + "\n", + "# We need the data row ID to create a batch\n", + "batch_datarows = [dr.uid for dr in list(dataset.export_data_rows())]\n", + "\n", + "## When creating a batch you can also setup the data rows priority\n", + "batch = batch_project.create_batch(\n", + " \"batch-demo\", # Each batch in a project must have a unique name\n", + " batch_datarows, # A list of data rows or data row ids\n", + " 5 # priority between 1(Highest) - 5(lowest)\n", + ")\n", + "print(\"Batch: \", batch)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" }, + "id": "IVwLUGRz-yrg", + "outputId": "b026daaa-ada8-4c49-80f0-5f1eb03ab896" + }, + "id": "IVwLUGRz-yrg", + "execution_count": 7, + "outputs": [ { - "cell_type": "code", - "execution_count": 7, - "id": "vanilla-diamond", - "metadata": {}, - "outputs": [], - "source": [ - "# Note setup_complete will be None if it fails.\n", - "print(project.setup_complete)\n", - "print(project.ontology())\n", - "print([ds.name for ds in project.datasets()])" - ] + "output_type": "stream", + "name": "stdout", + "text": [ + "Batch: \n" + ] + } + ] + }, + { + "cell_type": "markdown", + "id": "afraid-trademark", + "metadata": { + "id": "afraid-trademark" + }, + "source": [ + "### Review" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "vanilla-diamond", + "metadata": { + "id": "vanilla-diamond", + "colab": { + "base_uri": "https://localhost:8080/" }, + "outputId": "1b6883f4-9b3d-474d-b2c4-97afdf6473d5" + }, + "outputs": [ { - "cell_type": "code", - "execution_count": 8, - "id": "alpha-dayton", - "metadata": {}, - "outputs": [], - "source": [ - "print(f\"https://app.labelbox.com/projects/{project.uid}\")" - ] + "output_type": "stream", + "name": "stdout", + "text": [ + "2022-10-28 13:32:45+00:00\n", + "2022-10-28 13:32:50+00:00\n", + "\n", + "\n", + "['batch-demo']\n", + "['project_setup_demo']\n" + ] } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" + ], + "source": [ + "# Note setup_complete will be None if it fails.\n", + "print(batch_project.setup_complete)\n", + "print(dataset_project.setup_complete)\n", + "print(batch_project.ontology())\n", + "\n", + "print(dataset_project.ontology())\n", + "print([ds.name for ds in batch_project.batches()])\n", + "print([ds.name for ds in dataset_project.datasets()])" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "alpha-dayton", + "metadata": { + "id": "alpha-dayton", + "colab": { + "base_uri": "https://localhost:8080/" }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.8.2" + "outputId": "29225ad8-a6b9-43fd-f50b-2e935e1f1dfd" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "https://app.labelbox.com/projects/cl9sjavsl2oqx07w92abm9zy0\n", + "https://app.labelbox.com/projects/cl9sjaw2d2pgq07vddlfsgy6k\n" + ] } + ], + "source": [ + "print(f\"https://app.labelbox.com/projects/{batch_project.uid}\")\n", + "print(f\"https://app.labelbox.com/projects/{dataset_project.uid}\")" + ] + }, + { + "cell_type": "markdown", + "source": [ + "# Cleanup" + ], + "metadata": { + "id": "9YPXMzQBBHsL" + }, + "id": "9YPXMzQBBHsL" + }, + { + "cell_type": "code", + "source": [ + "# batch_project.delete()\n", + "# dataset_project.delete()\n", + "# dataset.delete()" + ], + "metadata": { + "id": "ueOV7oaxBGv0" + }, + "id": "ueOV7oaxBGv0", + "execution_count": 10, + "outputs": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "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": "3.8.2" }, - "nbformat": 4, - "nbformat_minor": 5 + "colab": { + "provenance": [], + "collapsed_sections": [] + } + }, + "nbformat": 4, + "nbformat_minor": 5 }