Container predefiniti per la previsione e la spiegazione

Vertex AI fornisce immagini container Docker che esegui come container predefiniti per fornire previsioni e spiegazioni da artefatti del modello addestrato. Questi container, organizzati per framework di machine learning (ML) e versione del framework, forniscono server di previsione HTTP che puoi utilizzare per fornire previsioni con una configurazione minima. In molti casi, utilizzare un container predefinito è più semplice che creare un container personalizzato per la previsione.

Questo documento elenca i container predefiniti per le previsioni e le spiegazioni e descrive come utilizzarli con gli elementi del modello che hai creato utilizzando la funzionalità di addestramento personalizzato di Vertex AI o gli elementi del modello che hai creato al di fuori di Vertex AI.

Norme e pianificazione dell'assistenza

Vertex AI supporta ogni versione del framework in base a una pianificazione per minimizzare le vulnerabilità di sicurezza. Esamina la pianificazione delle norme relative all'assistenza per comprendere le implicazioni delle date di ritiro del supporto e di fine della disponibilità.

Immagini container disponibili

Ognuna delle seguenti immagini container è disponibile in diversi repository Artifact Registry, che archiviano i dati in varie posizioni. Puoi utilizzare uno qualsiasi degli URI per un'immagine quando esegui l'addestramento personalizzato. Ogni URI fornisce la stessa immagine del container. Se utilizzi la console Google Cloud per creare una risorsa Model, la console seleziona l'URI più adatto alla posizione in cui utilizzi Vertex AI per ridurre la latenza.

TensorFlow

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine del patch e del supporto Fine della disponibilità Immagini supportate
2.13 Solo CPU 28 nov 2024 28 novembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-13:latest
2.13 GPU (CUDA 12.x) 28 nov 2024 28 novembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-13:latest
2.12 Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-12:latest
2.12 GPU (CUDA 11.x) 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-12:latest
2.11 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-11:latest
2.11 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-11:latest
2.10 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-10:latest
2.10 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-10:latest
2,9 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-9:latest
2,9 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-9:latest
2,8 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-8:latest
2,8 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-8:latest
2.7 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-7:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-7:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-7:latest
2.7 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-7:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-7:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-7:latest
2,6 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-6:latest
2,6 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-6:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-6:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-6:latest
2,5 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-5:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-5:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-5:latest
2,5 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-5:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-5:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-5:latest
2,4 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-4:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-4:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-4:latest
2,4 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-4:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-4:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-4:latest
2.3 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-3:latest
2.3 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-3:latest
2.2 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-2:latest
2.2 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
2.1 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-1:latest
2.1 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-2:latest
1,15 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf-cpu.1-15:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf-cpu.1-15:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf-cpu.1-15:latest
1,15 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/tf-gpu.1-15:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/tf-gpu.1-15:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/tf-gpu.1-15:latest

Runtime TensorFlow ottimizzato

Le seguenti immagini contenitore utilizzano il runtime TensorFlow ottimizzato. Per maggiori informazioni, consulta Utilizzare il runtime TensorFlow ottimizzato.

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine del patch e del supporto Fine della disponibilità Immagini supportate
ogni notte Solo CPU Non applicabile Non applicabile
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.nightly:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.nightly:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.nightly:latest
ogni notte GPU (CUDA 12.x) Non applicabile Non applicabile
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.nightly:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.nightly:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.nightly:latest
ogni notte Cloud TPU Non applicabile Non applicabile
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.nightly:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.nightly:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.nightly:latest
2,17 Solo CPU 11 luglio 2024 11 luglio 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-17:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-17:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-17:latest
2,17 GPU (CUDA 12.x) 11 luglio 2024 11 luglio 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-17:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-17:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-17:latest
2,17 Cloud TPU 11 luglio 2024 11 luglio 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-17:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-17:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-17:latest
2,16 Solo CPU 26 aprile 2024 26 aprile 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-16:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-16:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-16:latest
2,16 GPU (CUDA 12.x) 26 aprile 2024 26 aprile 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-16:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-16:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-16:latest
2,16 Cloud TPU 26 aprile 2024 26 aprile 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-16:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-16:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-16:latest
2,15 Solo CPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-15:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-15:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-15:latest
2,15 GPU (CUDA 12.x) 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-15:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-15:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-15:latest
2,15 Cloud TPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-15:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-15:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-tpu.2-15:latest
2,14 Solo CPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-14:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-14:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-14:latest
2,14 GPU (CUDA 12.x) 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-14:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-14:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-14:latest
2.13 Solo CPU 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-13:latest
2.13 GPU (CUDA 11.x) 15 agosto 2024 15 agosto 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-13:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-13:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-13:latest
2.12 Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-12:latest
2.12 GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-12:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-12:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-12:latest
2.11 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-11:latest
2.11 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-11:latest
2.10 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-10:latest
2.10 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-10:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-10:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-10:latest
2,9 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-9:latest
2,9 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-9:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-9:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-9:latest
2,8 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-cpu.2-8:latest
2,8 GPU (CUDA 11.x) 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-8:latest
  • europe-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-8:latest
  • asia-docker.pkg.dev/vertex-ai-restricted/prediction/tf_opt-gpu.2-8:latest

PyTorch

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine del patch e del supporto Fine della disponibilità Immagini supportate
2.1 (Python 3.9) Solo CPU 1° dic 2024 1 dicembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-1:latest
2.1 (Python 3.9) GPU (CUDA 12.x) 1° dic 2024 1 dicembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-1:latest
2.1 (Python 3.9) Cloud TPU 1° dic 2024 1 dicembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-tpu.2-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-tpu.2-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-tpu.2-1:latest
2.0 (Python 3.9) Solo CPU 27 lug 2024 27 luglio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-0:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-0:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.2-0:latest
2.0 (Python 3.9) GPU (CUDA 11.x) 27 lug 2024 27 luglio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-0:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-0:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.2-0:latest
1.13 (Python 3.8) Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-13:latest
1.13 (Python 3.8) GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-13:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-13:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-13:latest
1,12 Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-12:latest
1,12 GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-12:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-12:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-12:latest
1,11 Solo CPU 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-cpu.1-11:latest
1,11 GPU (CUDA 11.x) 15 maggio 2024 15 maggio 2025
  • us-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-11:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-11:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/pytorch-gpu.1-11:latest

scikit-learn

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine del patch e del supporto Fine della disponibilità Immagini supportate
1.3 (Python 3.10) Solo CPU 28 nov 2024 28 novembre 2025
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-3:latest
1.2 (Python 3.10) Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-2:latest
1,0 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-0:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-0:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.1-0:latest
0,24 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-24:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-24:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-24:latest
0,23 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-23:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-23:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-23:latest
0,22 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-22:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-22:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-22:latest
0,20 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-20:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-20:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/sklearn-cpu.0-20:latest

XGBoost

Versione framework ML Acceleratori supportati (e versione CUDA, se applicabile) Data di fine del patch e del supporto Fine della disponibilità Immagini supportate
1.7 (Python 3.10) Solo CPU 30 giugno 2024 30 giugno 2025
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-7:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-7:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-7:latest
1.6 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-6:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-6:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-6:latest
1,5 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-5:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-5:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-5:latest
1.4 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-4:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-4:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-4:latest
1.3 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-3:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-3:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-3:latest
1.2 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-2:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-2:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-2:latest
1.1 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-1:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-1:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.1-1:latest
0,90 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-90:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-90:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-90:latest
0,82 Solo CPU 15 novembre 2023 15 novembre 2024
  • us-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-82:latest
  • europe-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-82:latest
  • asia-docker.pkg.dev/vertex-ai/prediction/xgboost-cpu.0-82:latest

Utilizzare un container predefinito

Puoi specificare un contenitore predefinito per le previsioni quando crei una risorsa TrainingPipeline personalizzata che carica un Model o quando importi gli elementi del modello come Model.

Per utilizzare uno di questi contenitori predefiniti, devi salvare il modello come uno o più elementi del modello conformi ai requisiti del contenitore predefinito. Per ulteriori informazioni, consulta la sezione Esportare gli elementi del modello per la previsione.

I seguenti notebook mostrano come utilizzare un contenitore predefinito per generare le predizioni.

Che cosa vuoi fare? Notebook
Addestrare e pubblicare un modello TensorFlow utilizzando un container predefinito Addestramento personalizzato e previsione online
Pubblicare un modello PyTorch utilizzando un container predefinito Pubblicazione di modelli di immagini PyTorch con container predefiniti su Vertex AI
Pubblicare un modello di diffusione stabile utilizzando un container predefinito Esegui il deployment e ospita un modello di diffusione stabile su Vertex AI

Notebooks

Passaggi successivi