Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Tambahkan kemampuan machine learning ke aplikasi Anda
Gunakan Firebase ML untuk melatih dan men-deploy model kustom, atau gunakan solusi siap pakai dengan Cloud Vision API.
plat_ios
plat_android
Deploy model kustom yang berjalan di perangkat
Baik memulai dengan model TensorFlow Lite yang sudah ada atau melatih model Anda sendiri, Anda dapat menggunakan deployment model Firebase ML untuk mendistribusikan model ke pengguna secara over the air (OTA). Hal ini mengurangi ukuran penginstalan aplikasi awal karena model didownload oleh perangkat hanya jika diperlukan. Ini juga memungkinkan Anda melakukan pengujian A/B pada beberapa model, mengevaluasi performanya, dan mengupdate model secara teratur tanpa harus memublikasikan ulang seluruh aplikasi. Cukup upload model Anda ke konsol Firebase. Selain itu, kami akan menangani hosting dan menayangkannya ke aplikasi Anda. Jika mau, Anda juga dapat men-deploy model langsung dari pipeline produksi ML atau notebook Colab menggunakan Firebase Admin SDK.
Bangun solusi untuk kasus penggunaan umum dengan API siap pakai
Firebase ML juga dilengkapi serangkaian API berbasis cloud yang siap digunakan: mengenali teks, melabeli gambar, dan mengidentifikasi bangunan terkenal. Tidak seperti API di perangkat, API ini memanfaatkan kecanggihan teknologi machine learning dari Google Cloud untuk memberikan tingkat akurasi yang tinggi. Anda cukup meneruskan data ke library, yang membuat permintaan dengan lancar ke model yang berjalan di Google Cloud, dan Anda akan mendapatkan informasi yang diperlukan–semuanya cukup dalam beberapa baris kode.
eBay Motors menggunakan Firebase ML untuk mengategorikan gambar dengan cepat, mengurangi biaya, dan meningkatkan kualitas pengalaman pengguna
eBay Motors memungkinkan pengguna menelusuri dan menemukan mobil yang dijual di wilayahnya. Pelajari bagaimana mereka menggunakan AutoML Vision Edge di Firebase ML untuk membuat model sendiri dan meningkatkan kualitas pengalaman pengguna.
Baca selengkapnya
arrow_forward
Dokumentasi
Learn how to get started with ML by reviewing our technical documentation.
[null,null,[],[],[],null,["Firebase Machine Learning\n^BETA^\n\nMachine learning for mobile developers \n[Get started](https://console.firebase.google.com/project/_/ml/apis) [View docs\n*arrow_forward*](/docs/ml) \n\nAdd machine learning capabilities to your app \nUse Firebase ML to train and deploy custom models, or use a more turn-key solution with the Cloud Vision APIs. \n*plat_ios* *plat_android* \n\nDeploy custom models that run on-device \nWhether you are starting with an existing [TensorFlow Lite model](https://www.tensorflow.org/lite/models) or training your own, you can use Firebase ML model deployment to distribute models to your users over the air. This reduces initial app installation size since models are downloaded by the device only when needed. It also allows you to A/B test multiple models, evaluate their performance and update models regularly without having to republish your entire app. Just [upload your model](/docs/ml/manage-hosted-models) to the Firebase console, and we'll take care of hosting and serving it to your app. Or if you prefer, you can deploy models directly from your ML production pipeline or Colab notebook [using the Firebase Admin SDK](/docs/ml/manage-hosted-models#manage_models_with_the_firebase_admin_sdk). \n\nSolve for common use cases with turn-key APIs \nFirebase ML also comes with a set of ready-to-use cloud-based APIs for common mobile use cases: [recognizing text](/docs/ml/recognize-text), [labeling images](/docs/ml/label-images), and [recognizing landmarks](/docs/ml/recognize-landmarks). Unlike on-device APIs, these APIs leverage the power of Google Cloud's machine learning technology to give a high level of accuracy. You simply pass in data to the library, which seamlessly makes a request to models running on Google Cloud, and get back the information you need--all in a few lines of code. \nCase Studies \n\neBay Motors uses Firebase ML to quickly categorize images, reduce costs and improve user experience\n\n\neBay Motors allows users to search and find cars for sale in their area. Learn how they used AutoML Vision Edge in Firebase ML to create their own model and improve the user experience.\n[Read more\n*arrow_forward*](/case-studies/ebay) \n\nDocumentation \nLearn how to get started with ML by reviewing our technical documentation. \n[View docs](/docs/ml) \n\nPricing \nUnderstand ML pricing. \n[View pricing](/pricing#firebase-ml) \nTry Firebase today\n\n\nIntegrating it into your app is easy.\n[Get started](https://console.firebase.google.com/) \n\nAll Firebase products \n\nBuild\n\n- [App Check](/products/app-check)\n- [App Hosting](/products/app-hosting)\n- [Authentication](/products/auth)\n- [Cloud Functions](/products/functions)\n- [Cloud Storage](/products/storage)\n- [Data Connect](/products/data-connect)\n- [Extensions](/products/extensions)\n- [Firestore](/products/firestore)\n- [Firebase ML](/products/ml)\n- [Genkit](https://genkit.dev/)\n- [Hosting](/products/hosting)\n- [Realtime Database](/products/realtime-database)\n- [Firebase AI Logic client SDKs](/products/firebase-ai-logic)\n\n[Generative AI](/products/generative-ai) \n\nRun\n\n- [A/B Testing](/products/ab-testing)\n- [App Distribution](/products/app-distribution)\n- [Cloud Messaging](/products/cloud-messaging)\n- [Crashlytics](/products/crashlytics)\n- [Google Analytics](/products/analytics)\n- [In-App Messaging](/products/in-app-messaging)\n- [Performance Monitoring](/products/performance)\n- [Remote Config](/products/remote-config)\n- [Test Lab](/products/test-lab)"]]
