{"version":1,"pages":[{"id":"-M78aqN4NegnYah0nCbW","title":"Picsellia","pathname":"/picsellia","siteSpaceId":"sitesp_RbtyK","description":"Welcome to Picsell.ia, your new go-to platform for your AI projects. It doesn't matter if you are an ML professional,  an AI researcher or an aspiring data scientist, we got you covered."},{"id":"-Ma2aeW26v1QtD3dt7R7","title":"Getting started","pathname":"/picsellia/getting-started-2","siteSpaceId":"sitesp_RbtyK","description":"Here are a list of tutorials covering a range of use-cases you might want to work on without reading all of the documentation"},{"id":"-MSDKlOWuNBUr30s8eaz","title":"Start using Picsellia","pathname":"/picsellia/getting-started-2/start-using-picsell.ia","siteSpaceId":"sitesp_RbtyK","description":"Here we will describe the few steps that will help you discover all the parts of Picsell.ia, this will follow the onboarding that you should see when you first connect to the platform.","breadcrumbs":[{"label":"Getting started"}]},{"id":"-MSE9tMams4w4-dAmWc2","title":"Create, annotate, review a Dataset","pathname":"/picsellia/getting-started-2/create-annotate-review-a-dataset","siteSpaceId":"sitesp_RbtyK","description":"In this tutorial we will go through the creation of a training-ready dataset from raw images.","breadcrumbs":[{"label":"Getting started"}]},{"id":"-MTA-r-SiE0O36htTopK","title":"Create a new Dataset Version with merged labels","pathname":"/picsellia/getting-started-2/create-a-new-dataset-version-with-merged-labels","siteSpaceId":"sitesp_RbtyK","description":"Here, we will learn how to create a new Dataset version with less labels in order to specify a model","breadcrumbs":[{"label":"Getting started"}]},{"id":"-MOWjSmIyzaQ1IoUXgL2","title":"Train a custom Object Detection model","pathname":"/picsellia/getting-started-2/train-a-custom-object-detection-model","siteSpaceId":"sitesp_RbtyK","description":"Here, we will see how to perform transfer learning from a pre-trained model on your own dataset the easiest way ever !","breadcrumbs":[{"label":"Getting started"}]},{"id":"-Mkl8tCF1eIiciqlJOeK","title":"Train a custom Classification model","pathname":"/picsellia/getting-started-2/train-a-custom-classification-model","siteSpaceId":"sitesp_RbtyK","description":"In this tutorial, we will see how to train and iterate over an image classification model, from image annotation to training and test !","breadcrumbs":[{"label":"Getting started"}]},{"id":"-MSSlxHathHS-4P-9MDA","title":"Deploy model in production (Tensorflow only)","pathname":"/picsellia/getting-started-2/deploy-model-in-production-tensorflow-only","siteSpaceId":"sitesp_RbtyK","description":"In this tutorial, we will see how to deploy and monitor your model using Picsell.ia, from your saved model files to an inference ready production model","breadcrumbs":[{"label":"Getting started"}]},{"id":"-MWAST25iCTvstW44x5n","title":"Feedback loop - Send predictions from models to Datalake or Datasets","pathname":"/picsellia/getting-started-2/feedback-loop-send-predictions-from-models-to-datalake-or-datasets","siteSpaceId":"sitesp_RbtyK","description":"Here, we will learn how to send the images and predictions (bounding boxes, masks, classification) from the models you deployed, back to Picsell.ia directly in your Datalake or Datasets","breadcrumbs":[{"label":"Getting started"}]},{"id":"-Ma2aw65RkiqQpgou32U","title":"Data Management","pathname":"/picsellia/data-management","siteSpaceId":"sitesp_RbtyK","description":"One of the main feature of Picsellia is Data Management, from storage to versioning through annotation, we will cover everything in this section"},{"id":"-MQwZKCJKZYlcQYvnzo6","title":"Upload assets to your Lake","pathname":"/picsellia/data-management/upload-assets-to-your-lake","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Data Management"}]},{"id":"-MQwauz0f4PgUJmYh3tU","title":"Edit Tags for Pictures","pathname":"/picsellia/data-management/edit-tags-for-pictures","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Data Management"}]},{"id":"-MQwWfl-5guVMg3Vib9X","title":"Create a Dataset","pathname":"/picsellia/data-management/create-a-dataset","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Data Management"}]},{"id":"-MQwjTDAASQvz6D1hoFx","title":"Add data to a Dataset","pathname":"/picsellia/data-management/add-data-to-a-dataset","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Data Management"}]},{"id":"-MQwl0xj6l2R25vTV1fU","title":"Create a new Dataset version","pathname":"/picsellia/data-management/create-a-new-dataset-version","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Data Management"}]},{"id":"-MQwmyn48Fy0BrkqiZDp","title":"Configure your Labels","pathname":"/picsellia/data-management/configure-your-labels","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Data Management"}]},{"id":"-MQwrGtdn-yEjSa_xU6N","title":"Import annotation from other Dataset version","pathname":"/picsellia/data-management/import-annotation-from-other-dataset-version","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Data Management"}]},{"id":"-Ma2b8QDfI9VcM9ZLS8w","title":"Experiment Tracking","pathname":"/picsellia/experiment-tracking","siteSpaceId":"sitesp_RbtyK","description":"The second main feature on Picsellia is the ability to track all the experiments that will lead you to the best version of your models, let's discover it !"},{"id":"-MOMWHeUGYRa_LbGNxuQ","title":"Initialize an experiment","pathname":"/picsellia/experiment-tracking/initialize-an-experiment","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MOMn5qnCaiwLdADqaq0","title":"Checkout an experiment","pathname":"/picsellia/experiment-tracking/checkout-an-experiment","siteSpaceId":"sitesp_RbtyK","description":"Here we will see how to retrieve an experiment, it is useful if you want to work on an experiment created in our UI or if you need to download your saved model weights for inference for example...","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MOMvMiM1qO6odDZXzQz","title":"Log your results to Picsell.ia","pathname":"/picsellia/experiment-tracking/log-your-results-to-picsell.ia","siteSpaceId":"sitesp_RbtyK","description":"We will see how you can store any variable, function output, array, image, and visualize it in your experiment's tab in our platform.","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MON5vfgBqCOwVLEaHAR","title":"Store your files to Picsell.ia","pathname":"/picsellia/experiment-tracking/store-your-files-to-picsell.ia","siteSpaceId":"sitesp_RbtyK","description":"Here we will learn how to store any file that you generate during your experiment on Picsell.ia so you and your team can access it anywhere, anytime.","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MXGlt5fmo_gCFRxJ-li","title":"Evaluate your models","pathname":"/picsellia/experiment-tracking/evaluate-your-models","siteSpaceId":"sitesp_RbtyK","description":"In this page, we are going to explain how you can leverage the Picsellia Python SDK and the platform to evaluate your models and identify edge-cases easily.","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MONDvXNY3ZPib3GAZZt","title":"Retrieve and update your assets","pathname":"/picsellia/experiment-tracking/retrieve-and-update-your-assets","siteSpaceId":"sitesp_RbtyK","description":"Here we will learn how to interact with the data and file assets that we have saved to the platform.","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MPFLJTp2_EIsjPZWdlT","title":"Publish your model","pathname":"/picsellia/experiment-tracking/publish-your-model","siteSpaceId":"sitesp_RbtyK","description":"Here we will see how to publish a version of your experiment so it can be used outside of the project scope and deployed for production use","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MQlrB1fLKIIV-CjgDZY","title":"Namespace","pathname":"/picsellia/experiment-tracking/namespace","siteSpaceId":"sitesp_RbtyK","description":"This page describes all of the name of the reserved namespace for experiments and their specificity","breadcrumbs":[{"label":"Experiment Tracking"}]},{"id":"-MZCMRJv_pbllD2xL3pd","title":"Hyperparameter tuning","pathname":"/picsellia/hyperparameter-tuning","siteSpaceId":"sitesp_RbtyK","description":"In this section we will dive in-depth into hyperparameter tuning which is the natural expansion of experiment tracking."},{"id":"-MZrttiBjFofeJ706Oth","title":"Overview","pathname":"/picsellia/hyperparameter-tuning/overview","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Hyperparameter tuning"}]},{"id":"-MZlOCtxS4fnjuHHvgl2","title":"Install Picsell CLI","pathname":"/picsellia/hyperparameter-tuning/install-picsell-cli","siteSpaceId":"sitesp_RbtyK","description":"The CLI Picsellia is the simplest way to manage and orchestrate your training in order to find your best hyper-parameters","breadcrumbs":[{"label":"Hyperparameter tuning"}]},{"id":"-MZCMWp1OGSz4ET7Vbt5","title":"Config","pathname":"/picsellia/hyperparameter-tuning/config","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Hyperparameter tuning"}]},{"id":"-MZqJGvLbTONUdn4BE15","title":"Launch your Hyperparameters tuning","pathname":"/picsellia/hyperparameter-tuning/launch-your-hyperparameters-tuning","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Hyperparameter tuning"}]},{"id":"-Ma2b_Sw32W0hAVopQ5u","title":"Models","pathname":"/picsellia/models-1","siteSpaceId":"sitesp_RbtyK","description":"One important part of Picsellia is the ability to store, share, re-use and deploy your trained models, here we will cover this topic."},{"id":"-MUIdlqFuC9bXMg8gs4Y","title":"Model HUB","pathname":"/picsellia/models-1/model-hub","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"Models"}]},{"id":"-Ma2aoM_XeAA-pdeSnRP","title":"References","pathname":"/picsellia/references-1","siteSpaceId":"sitesp_RbtyK","description":"Here you will discover how to interact with the platform with your own systems"},{"id":"-M7Cj_YVshw8kti7dP8x","title":"API Reference","pathname":"/picsellia/references-1/api-reference","siteSpaceId":"sitesp_RbtyK","description":"","breadcrumbs":[{"label":"References"}]},{"id":"-MORSNBvTU2p3o7NDonX","title":"Python SDK Reference","pathname":"/picsellia/references-1/python-sdk-reference-1","siteSpaceId":"sitesp_RbtyK","description":"Here we will describe every method of the picsellia package","breadcrumbs":[{"label":"References"}]},{"id":"-MOVnTwuOMAJQG2GU5h_","title":"Python Training Reference","pathname":"/picsellia/references-1/python-training-reference","siteSpaceId":"sitesp_RbtyK","description":"This page describes all the methods from our different package (picsellia_tf1, picsellia_tf2) that simplifies training for the different AI frameworks.","breadcrumbs":[{"label":"References"}]},{"id":"-Ma2dqbqQ9JXktonR_Kr","title":"Organization","pathname":"/picsellia/organization","siteSpaceId":"sitesp_RbtyK","description":"Picsellia is made for you to work with your team and is suited to be used in any organization of any size, here we will describe how it works and what depend of your organization or not."}]}