

Deploy PaliGemma to GCP Compute Engine

Deploy your models with Roboflow

Hosted or on-device deployment

SDKs optimized for maximum performance

Extensive documentation

Get started for free

Learn More

How to Deploy PaliGemma to GCP Compute Engine

In this guide, we are going to show how to deploy a

PaliGemma

model to

GCP Compute Engine

using Roboflow Inference. Inference is a high-performance inference server with which you can run a range of vision models, from YOLOv8 to CLIP to CogVLM.

To deploy a

PaliGemma

model to

GCP Compute Engine

, we will:

1. Set up our computing environment
2. Download the Roboflow Inference Server
3. Try out our model on an example image

Let's get started!

In this guide, we are going to show how to deploy a

PaliGemma

model to

GCP Compute Engine

using the Roboflow Inference Server. This SDK works with

PaliGemma

models trained on both Roboflow and in custom training processes outside of Roboflow.

To deploy a

PaliGemma

model to

GCP Compute Engine

, we will:

1. Train a model on (or upload a model to) Roboflow
2. Download the Roboflow Inference Server
3. Install the Python SDK to run inference on images
4. Try out the model on an example image

Let's get started!

Train a Model on or Upload a Model to Roboflow

First, create a Roboflow account and create a new project. When you have created a new project, upload your project data, then generate a new dataset version. With that version ready, you can upload your model weights to Roboflow.

Download the Roboflow Python SDK:

pip install roboflow

Then, use the following script to upload your model weights:

from roboflow import Roboflow

home = "/path/to/project/folder"

rf = Roboflow(api_key=os.environ["ROBOFLOW_API_KEY"])
project = rf.workspace().project("PROJECT_ID")

project.version(PROJECT_VERSION).deploy(model_type="yolov5", model_path=f"/{home}/yolov5/runs/train/")

Read the Roboflow model weight upload documentation for more information about uploading model weights.

You will need your project name, version, API key, and model weights. The following documentation shows how to retrieve your API key and project information:

- Retrieve your Roboflow project name and version
- Retrieve your API key

Change the path in the script above to the path where your model weights are stored.

When you have configured the script above, run the code to upload your weights to Roboflow.

Now you are ready to start deploying your model.

Set up a GCP Compute Engine Virtual Machine

You will need to upload your trained PaliGemma model to Roboflow. This will allow you to download your model weights directly into your Inference deployment, whether you use the SDK or the HTTP API with Docker. To learn how to upload your model weights, refer to our model weight upload guide.

Open GCP Compute Engine and click the “Create Instance” button to create a virtual machine.

Next, you need to configure your instance. The requirements for configuration depend on your use case. If you are deploying a server for production, you may opt for a more powerful machine configuration. If you are testing a model and plan to deploy on another machine in the future, you may instead opt to deploy a less powerful machine.

You must deploy on a system with an NVIDIA GPU to run CogVLM with Inference.

A cost panel will appear on the right of the screen that estimates the cost of the machine you are deploying.

Fill out the required fields to configure your virtual machine. Then, click the “Create” button to create a virtual machine. It will take a few moments before your machine is ready. You can view the status from the Compute Engine Instances page.

When your virtual machine has been deployed, click on the machine name in the list of virtual machines on the Compute Engine Instances page.

To sign in using SSH in a terminal, click the arrow next to the SSH button and click “View gcloud command” If you have not already installed gcloud, follow the gcloud installation and configuration instructions to get started.

Download Roboflow Inference

The Roboflow Inference Server allows you to deploy computer vision models to a range of devices, including

GCP Compute Engine

.

You can run Roboflow Inference in Docker, or via the Python SDK.

For this guide, we will run Inference with Docker and use the Python SDK to interface with our Docker deployment. We will deploy our model on a

GCP Compute Engine

.

To install Inference and set up an Inference server in Docker, run:
‍


pip install inference
inference server start

Now you have the Roboflow Inference Server running, you can use your model on

GCP Compute Engine

.

For a Jetson deployment, using Docker is highly recommended since everything has to be installed special depending on your Jetpack version. Absent Docker, it is easy to accidentally do these installs incorrectly and need to reflash everything to the device.

Run Inference on an Image

You can run inference on images with Roboflow Inference.

Create a new Python file and add the following code:

# import client from inference sdk
from inference_sdk import InferenceHTTPClient
# import PIL for loading image
from PIL import Image
# import os for getting api key from environment
import os

# set the project_id, model_version, image_url
project_id = "soccer-players-5fuqs"
model_version = 1
filename = "path/to/local/image.jpg"

# create a client object
client = InferenceHTTPClient(
    api_url="http://localhost:9001",
    api_key=os.environ["API_KEY"],
)

# load the image
pil_image = Image.open(filename)

# run inference
results = client.infer(pil_image, model_id=f"{project_id}/{model_version}")

print(results)

Substitute the model name and version with the values associated with your Roboflow account and project, then run the script.

Retrieve your Roboflow project name and version

This code will return a Python object with results from your model.

You can process these results and plot them on an image with the supervision Python package:


detections = sv.Detections.from_inference(results[0])

box_annotator = sv.BoxAnnotator()
label_annotator = sv.LabelAnnotator()

annotated_image = box_annotator.annotate(
    scene=image, detections=detections)
annotated_image = label_annotator.annotate(
    scene=annotated_image, detections=detections)

sv.plot_image(image=annotated_image, size=(16, 16))

Run Inference on a Video

You can run inference on videos with Roboflow Inference and the InferencePipeline feature.

Create a new Python file and add the following code:

# Import the InferencePipeline object
from inference import InferencePipeline
# Import the built in render_boxes sink for visualizing results
from inference.core.interfaces.stream.sinks import render_boxes

# initialize a pipeline object
pipeline = InferencePipeline.init(
    model_id="rock-paper-scissors-sxsw/11", # Roboflow model to use
    video_reference=0, # Path to video, device id (int, usually 0 for built in webcams), or RTSP stream url
    on_prediction=render_boxes, # Function to run after each prediction
)
pipeline.start()
pipeline.join()

Substitute the model name and version with the values associated with your Roboflow account and project, then run the script.

Retrieve your Roboflow project name and version

This code will run a model on frames from a webcam stream. To use RTSP, set the video_reference value to an RTSP stream URL. To use video, set the video_reference value to a video file path.

Predictions are annotated using the render_boxes helper function. You can specify any function to process each prediction in the on_prediction parameter.

To learn how to define your own callback function with custom logic, refer to the Define Custom Prediction Logic documentation.

Learn how to deploy models to other devices

Below, you can find our guides on how to deploy

PaliGemma

models to other devices.

Deploy PaliGemma to GCP Compute Engine

Deploy PaliGemma to AWS EC2

Documentation

The following resources are useful reference material for working with your model using Roboflow and the Roboflow Inference Server.