Treinamento personalizado do Hello: limpar seu projeto
Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
Nesta página, você vai aprender a limpar os recursos do Google Cloud que criou para treinar o modelo de classificação de imagens e exibir previsões com ele.
Cada página pressupõe que você já tenha realizado as instruções das páginas anteriores do tutorial.
O restante deste documento pressupõe que você está usando o mesmo ambiente
do Cloud Shell criado ao seguir a primeira página deste
tutorial. Se a sessão original do Cloud Shell não estiver
mais aberta, será possível retornar ao ambiente fazendo o seguinte:
In the Google Cloud console, activate Cloud Shell.
Clique em hello_custom para acessar a página de detalhes do endpoint.
Na linha do seu modelo, hello_custom, clique em Cancelar a implantação do modelo
delete.
Na caixa de diálogo Cancelar a implantação do modelo do endpoint, clique em Cancelar a implantação.
Excluir o endpoint
Antes de excluir um endpoint, é necessário remover a implantação do modelo do
endpoint. Depois de excluir o endpoint, não será possível reutilizar o nome dele por até sete dias.
Depois de remover a implantação do modelo do endpoint, faça o seguinte
para excluir o endpoint:
No console Google Cloud , na seção "Vertex AI", acesse
a página Endpoints.
Encontre a linha do modelo, hello_custom. Nessa linha, clique em Ver mais
more_vert. Em seguida,
clique em Excluir modelo.
Na caixa de diálogo Excluir modelo, clique em Excluir.
Excluir o pipeline de treinamento personalizado e o job
O pipeline de treinamento e o job personalizado são apenas registros do treinamento que
aconteceu anteriormente. Se você quiser excluir o job personalizado, faça o seguinte:
No console Google Cloud , na seção "Vertex AI", acesse
a página Pipelines de treinamento.
Encontre a linha do pipeline de treinamento, hello_custom. Nessa linha,
clique em Ver mais more_vert. Em seguida, clique em Excluir pipeline de
treinamento.
Na caixa de diálogo Excluir job de treinamento, clique em Excluir.
Para acessar a página Jobs personalizados, clique em Job personalizado no
consoleGoogle Cloud ou no seguinte link:
Encontre a linha do job personalizado, hello_custom-custom-job. Nessa linha,
clique em Ver mais more_vert. Em seguida, clique em Excluir job personalizado.
Na caixa de diálogo Excluir job de treinamento, clique em Excluir.
[[["Fácil de entender","easyToUnderstand","thumb-up"],["Meu problema foi resolvido","solvedMyProblem","thumb-up"],["Outro","otherUp","thumb-up"]],[["Difícil de entender","hardToUnderstand","thumb-down"],["Informações incorretas ou exemplo de código","incorrectInformationOrSampleCode","thumb-down"],["Não contém as informações/amostras de que eu preciso","missingTheInformationSamplesINeed","thumb-down"],["Problema na tradução","translationIssue","thumb-down"],["Outro","otherDown","thumb-down"]],["Última atualização 2025-08-19 UTC."],[],[],null,["# Hello custom training: Clean up your project\n\nThis page guides you through cleaning up the Google Cloud resources that you\ncreated to train your image classification model and serve predictions from it.\nThis tutorial has several pages:\n\n\u003cbr /\u003e\n\n1. [Setting up your project and environment.](/vertex-ai/docs/tutorials/image-classification-custom)\n\n2. [Training a custom image classification\n model.](/vertex-ai/docs/tutorials/image-classification-custom/training)\n\n3. [Serving predictions from a custom image classification\n model.](/vertex-ai/docs/tutorials/image-classification-custom/serving)\n\n4. Cleaning up your project.\n\nEach page assumes that you have already performed the instructions from the\nprevious pages of the tutorial.\nThe rest of this document assumes that you are using the same Cloud Shell environment that you created when following the [first page of this\ntutorial](/vertex-ai/docs/tutorials/image-classification-custom). If your original Cloud Shell session is no longer open, you can return to the environment by doing the following:\n\n\u003cbr /\u003e\n\n1. In the Google Cloud console, activate Cloud Shell.\n\n [Activate Cloud Shell](https://console.cloud.google.com/?cloudshell=true)\n2. In the Cloud Shell session, run the following command:\n\n ```bash\n cd hello-custom-sample\n ```\n\nDelete Vertex AI resources\n--------------------------\n\nThis section describes how to delete all of the Vertex AI resources\nthat you created for this tutorial.\n\n### Undeploy your model from your endpoint\n\nThis section describes how to undeploy your model from your endpoint. You can\nthink about this action as a way of disconnecting your model from your endpoint.\n\nYou must follow this section before you can [delete your\nendpoint](#delete-endpoint) or [delete your model](#delete-model).\n\n1. In the Google Cloud console, in the Vertex AI section, go to\n the **Endpoints** page.\n\n [Go to Endpoints](https://console.cloud.google.com/vertex-ai/endpoints)\n2. Click `hello_custom` to go to the endpoint details page.\n\n3. On the row for your model, `hello_custom`, click **Undeploy model\n delete**.\n\n4. In the **Undeploy model from endpoint** dialog, click **Undeploy**.\n\n### Delete your endpoint\n\nBefore you delete an endpoint, you must [undeploy your model from your\nendpoint](#undeploy-model). After you've deleted your endpoint, you won't\nbe able to re-use that endpoint name for up to 7 days.\n\nAfter you've undeployed your model from the endpoint, do the following\nto delete your endpoint:\n\n1. In the Google Cloud console, in the Vertex AI section, go to\n the **Endpoints** page.\n\n [Go to Endpoints](https://console.cloud.google.com/vertex-ai/endpoints)\n2. Find your the row of your endpoint, `hello_custom`, again. On that row, click\n **View more more_vert** . Then click **Remove endpoint**.\n\n3. In the **Remove endpoint** dialog, click **Confirm**.\n\n### Delete your model\n\nBefore you follow this section, you must [undeploy your model from your\nendpoint](#undeploy-model). Afterward, do the following to delete your model:\n\n1. In the Google Cloud console, in the Vertex AI section, go to\n the **Models** page.\n\n [Go to Models](https://console.cloud.google.com/vertex-ai/models)\n2. Find your the row of your model, `hello_custom`. On that row, click **View\n more more_vert** . Then\n click **Delete model**.\n\n3. In the **Delete model** dialog, click **Delete**.\n\n### Delete your custom training pipeline and job\n\nYour training pipeline and custom job are just records of the training that\nhappened earlier. If you want to delete your custom job, do the following:\n\n1. In the Google Cloud console, in the Vertex AI section, go to\n the **Training pipelines** page.\n\n [Go to Training pipelines](https://console.cloud.google.com/vertex-ai/training/training-pipelines)\n2. Find your the row of your training pipeline, `hello_custom`. On that row,\n click **View more more_vert** . Then click **Delete training\n pipeline**.\n\n3. In the **Delete training job** dialog, click **Delete**.\n\n4. To go to the **Custom jobs** page, click **Custom job** in the\n Google Cloud console, or click the following link:\n\n [Go to Custom jobs](https://console.cloud.google.com/vertex-ai/training/custom-jobs)\n5. Find your the row of your custom job, `hello_custom-custom-job`. On that row,\n click **View more more_vert** . Then click **Delete custom job**.\n\n6. In the **Delete training job** dialog, click **Delete**.\n\nClean up your Cloud Shell session\n---------------------------------\n\nCloud Shell incurs no charges, and it [automatically deletes your home\ndisk after a period of inactivity](/shell/docs/limitations). However, if you\nplan to use Cloud Shell for other purposes in the near future, you\nmight want to manually remove the files that you created for this tutorial.\n\nIn your Cloud Shell session, run the following commands: \n\n cd ..\n rm -rf hello-custom-sample\n\nDelete your Cloud Storage bucket\n--------------------------------\n\nIn your Cloud Shell session, run the following command: \n\n gcloud storage rm gs://\u003cvar translate=\"no\"\u003eBUCKET_NAME\u003c/var\u003e --recursive --continue-on-error\n\nReplace \u003cvar translate=\"no\"\u003eBUCKET_NAME\u003c/var\u003e with the name of the Cloud Storage\nbucket that you created when reading the [first page of this\ntutorial](/vertex-ai/docs/tutorials/image-classification-custom).\n\nDelete your Cloud Run function\n------------------------------\n\nIn your Cloud Shell session, run the following command: \n\n gcloud functions delete classify_flower --region=us-central1 --quiet\n\nWhat's next\n-----------\n\n- To learn about additional ways to train ML models on Vertex AI,\n try one of the other [Vertex AI tutorials](/vertex-ai/docs/tutorials).\n\n- Read an [overview of how Vertex AI\n works](/vertex-ai/docs/start/introduction-unified-platform)."]]