xiaohei/model_garden
1
0
Fork 0
mirror of https://github.com/GoogleCloudPlatform/vertex-ai-samples.git synced 2026-09-26 14:42:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixed the deployment quota check and modified the documentation.

Browse Source 
PiperOrigin-RevId: 832174331
This commit is contained in:
Vertex MG Team
2025-11-13 23:14:25 -08:00
committed by Copybara-Service
parent 9e96a3da67
commit 646532ea69
1 changed files with 32 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/community/model_garden/model_garden_remote_sensing_deployment.ipynb
+32 -30
View File
@@ -128,7 +128,7 @@
" platform: str,\n",
" machine_type: str,\n",
" accelerator_type: str,\n",
" accelerator_count,\n",
" accelerator_count: int,\n",
" service_account: str = None,\n",
" use_dedicated_endpoint: bool = False,\n",
" min_replica_count: int = 1,\n",
@@ -141,7 +141,7 @@
" model_type: The model type to deploy, either MAMMUT or OWLVIT.\n",
" model_mode: The model mode to deploy, e.g. COMBINED, IMAGE_ONLY or\n",
" TEXT_ONLY.\n",
" platform: The deployment platform, CPU, NVIDIA_L4 or NVIDIA_A100_80GB.\n",
" platform: The deployment platform, either \"cpu\" or \"gpu\".\n",
" machine_type: The instance machine type to use, see\n",
" https://cloud.google.com/compute/docs/machine-resource\n",
" accelerator_type: The GPU type to deploy, defaults to NVIDIA_L4, see\n",
@@ -150,13 +150,15 @@
" \"\"\"\n",
" model_id, model_name, model_path = MODEL_CONFIGS[model_type]\n",
"\n",
" common_util.check_quota(\n",
" project_id=PROJECT_ID,\n",
" region=REGION,\n",
" accelerator_type=accelerator_type,\n",
" accelerator_count=accelerator_count,\n",
" is_for_training=False,\n",
" )\n",
" if platform != \"cpu\":\n",
" # Check quota only when using accelerators (GPU).\n",
" common_util.check_quota(\n",
" project_id=PROJECT_ID,\n",
" region=REGION,\n",
" accelerator_type=accelerator_type,\n",
" accelerator_count=accelerator_count,\n",
" is_for_training=False,\n",
" )\n",
"\n",
" model = aiplatform.Model.upload(\n",
" display_name=f\"{name}-model\",\n",
@@ -227,23 +229,6 @@
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "OXApz2t7YCfZ"
},
"outputs": [],
"source": [
"# @title Cleanup Resources\n",
"# @markdown Delete the experiment models and endpoints to recycle the resources\n",
"# @markdown and avoid unnecessary continuous charges that may incur.\n",
"\n",
"endpoint.delete(force=True)\n",
"model.delete()"
]
},
{
"cell_type": "markdown",
"metadata": {
@@ -274,9 +259,6 @@
"source": [
"# @title Inference setup & utils.\n",
"\n",
"# @markdown If you've just deployed a new endpoint you can use it directly,\n",
"# @markdown otherwise specify an endpoint id to override it.\n",
"\n",
"import base64\n",
"import io\n",
"\n",
@@ -289,7 +271,10 @@
" return base64.b64encode(arr_bytes.getvalue()).decode(\"utf-8\")\n",
"\n",
"\n",
"# Override the endpoint, if kept empty uses the recently deployed endpoint.\n",
"# @markdown **(Optional)** Override the endpoint id.\n",
"# @markdown *Note: If kept empty uses the recently deployed endpoint.*\n",
"# @markdown *Note: Make sure to use the endpoid id from the previous cell output*\n",
"# @markdown * (Not the endpoint name used above)*\n",
"ENDPOINT_ID = \"\" # @param { 'type': 'string' }\n",
"use_dedicated_endpoint = True # @param { 'type' : 'boolean' }\n",
"\n",
@@ -410,6 +395,23 @@
")\n",
"print(result)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "quCzxT0WB_Ts"
},
"outputs": [],
"source": [
"# @title Cleanup Resources\n",
"# @markdown Delete the experiment models and endpoints to recycle the resources\n",
"# @markdown and avoid unnecessary continuous charges that may incur.\n",
"\n",
"endpoint.delete(force=True)\n",
"model.delete()"
]
}
],
"metadata": {