Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Firebase ML menyimpan set data pelatihan AutoML Anda dengan cara yang berbeda-beda, bergantung pada paket harga project Anda. Jika project Anda menggunakan paket harga Blaze, Firebase ML akan membuat bucket Cloud Storage baru di project Anda untuk menyimpan data AutoML Vision Edge. Jika project Anda menggunakan paket harga Spark, Firebase ML akan menyimpan data AutoML Vision Edge secara internal, bukan menggunakan Cloud Storage project Anda.
Jika Anda membuat set data selagi menggunakan paket harga Spark dan kemudian mengupgrade ke paket Blaze, set data Anda akan tersedia, tetapi akan diberlakukan batasan paket Spark (set data ini diberi label Spark datasets di Firebase console). Jika Anda ingin set data memanfaatkan fitur Blaze, seperti contoh pelatihan tidak terbatas (ditagih berdasarkan penggunaan penyimpanan), Anda harus memigrasikan set data Spark ke set data yang baru.
Untuk memigrasikan set data:
Buka bagian AutoML di Firebase console. (Pilih project Anda saat diminta.)
Di set data yang Anda ingin migrasikan, klik Lihat untuk membuka halaman detail, lalu klik Ekspor set data. Anda akan mendownload file zip yang berisi gambar dan label pelatihan set data.
Buat set data baru dengan mengupload file zip.
(Lihat Melatih model Anda.)
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Informasi yang saya butuhkan tidak ada","missingTheInformationINeed","thumb-down"],["Terlalu rumit/langkahnya terlalu banyak","tooComplicatedTooManySteps","thumb-down"],["Sudah usang","outOfDate","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Masalah kode / contoh","samplesCodeIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-09-06 UTC."],[],[],null,["\u003cbr /\u003e\n\nFirebase ML stores your AutoML training datasets differently, depending on\nyour project's pricing plan. When your project is on the Blaze pricing plan,\nFirebase ML creates a new Cloud Storage bucket in your project to store\nAutoML Vision Edge data. When your project is on the Spark pricing plan,\nFirebase ML stores your AutoML Vision Edge data internally instead of using\nyour project's Cloud Storage.\n| Firebase ML's AutoML Vision Edge features are deprecated. Consider using [Vertex AI](https://cloud.google.com/vertex-ai/docs/beginner/beginners-guide) to automatically train ML models, which you can either [export as TensorFlow\n| Lite models](https://cloud.google.com/vertex-ai/docs/export/export-edge-model) for on-device use or [deploy for cloud-based\n| inference](https://cloud.google.com/vertex-ai/docs/predictions/overview).\n\nIf you create a dataset while on the Spark pricing plan and later upgrade to the\nBlaze plan, your dataset will be available, but will still be subject to the\nlimitations of the Spark plan (these datasets are labeled **Spark datasets** in\nthe Firebase console). If you want your dataset to take advantage of Blaze\nfeatures, such as unlimited training examples (billed by storage use), you'll\nhave to migrate the Spark dataset to a new dataset.\n\nTo migrate a dataset:\n\n1. Open the [AutoML section](//console.firebase.google.com/project/_/ml/automl) of the\n Firebase console. (Select your project when prompted.)\n\n2. On the dataset you want to migrate, click **View** to open the details page,\n then click **Export dataset**. You will download a zip file containing the\n dataset's training images and labels.\n\n3. Create a new dataset by uploading the zip file.\n (See [Train your model](/docs/ml/train-image-labeler#train_the_model).)"]]
