You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
How to deploy trained model to images online? #784
Models: Training and Exporting. Train YOLOv5 and YOLOv8 models on your custom datasets and export them to various formats for deployment.
Integrations. Explore different integration options for your trained models, such as TensorFlow, ONNX, OpenVINO, CoreML, and PaddlePaddle.
Ultralytics HUB App. Learn about the Ultralytics App for iOS and Android, which allows you to run models directly on your mobile device.
iOS. Learn about YOLO CoreML models accelerated on Apple's Neural Engine on iPhones and iPads.
Android. Explore TFLite acceleration on mobile devices.
Inference API. Understand how to use the Inference API for running your trained models in the cloud to generate predictions.
If this is a 🐛 Bug Report, please provide screenshots and steps to reproduce your problem to help us get started working on a fix.
If this is a ❓ Question, please provide as much information as possible, including dataset, model, environment details etc. so that we might provide the most helpful response.
We try to respond to all issues as promptly as possible. Thank you for your patience!
Great to hear that you've successfully trained your model using Ultralytics HUB! Deploying your trained model to detect objects in a series of images online is straightforward. Here's how you can do it:
Export Your Model: First, ensure your trained model is exported. You can do this directly from the Ultralytics HUB. Navigate to your project, select the trained model, and look for the export options. You can export the model in various formats like ONNX, TorchScript, or CoreML depending on your deployment needs.
Use Ultralytics HUB API: Ultralytics HUB provides an API that allows you to perform inference on images. You can upload your images and get predictions using this API. Here’s a basic example of how you can use the API to detect objects in images:
importrequests# Define the API endpoint and your API keyapi_url='https://hub.ultralytics.com/api/v1/predict'api_key='your_api_key_here'# Load your imageimage_path='path_to_your_image.jpg'withopen(image_path, 'rb') asimage_file:
image_data=image_file.read()
# Make the requestresponse=requests.post(
api_url,
headers={'Authorization': f'Bearer {api_key}'},
files={'file': image_data}
)
# Check the responseifresponse.status_code==200:
predictions=response.json()
print(predictions)
else:
print(f"Error: {response.status_code}, {response.text}")
Web Application Integration: If you want to integrate this into a web application, you can use frameworks like Flask or Django (for Python) to create an endpoint that handles image uploads, calls the Ultralytics HUB API, and returns the predictions.
Ultralytics HUB App: You can also use the Ultralytics HUB App to preview and test your model directly on the platform. This is a great way to quickly validate your model's performance on new images.
👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.
For additional resources and information, please see the links below:
Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!
Thank you for your contributions to YOLO 🚀 and Vision AI ⭐
Hi @sylenola, revisiting this since HUB winds down on July 31, 2026: what you asked for — running your trained model on images online — is now built into Ultralytics Platform. Every model page has a Predict tab for browser inference with no local setup, and for batches of images you can create a dedicated endpoint and POST images to it from any language.
Hi @sylenola, running your trained model on images online is answered above and is now built into the Predict tab of every model on Ultralytics Platform. I'm closing this as resolved. Please reopen if you run into problems.
Activity
github-actions commentedon Jul 28, 2024
👋 Hello @sylenola, thank you for raising an issue about Ultralytics HUB 🚀! Please visit our HUB Docs to learn more:
If this is a 🐛 Bug Report, please provide screenshots and steps to reproduce your problem to help us get started working on a fix.
If this is a ❓ Question, please provide as much information as possible, including dataset, model, environment details etc. so that we might provide the most helpful response.
We try to respond to all issues as promptly as possible. Thank you for your patience!
pderrenger commentedon Jul 28, 2024
@sylenola hi there!
Great to hear that you've successfully trained your model using Ultralytics HUB! Deploying your trained model to detect objects in a series of images online is straightforward. Here's how you can do it:
Export Your Model: First, ensure your trained model is exported. You can do this directly from the Ultralytics HUB. Navigate to your project, select the trained model, and look for the export options. You can export the model in various formats like ONNX, TorchScript, or CoreML depending on your deployment needs.
Use Ultralytics HUB API: Ultralytics HUB provides an API that allows you to perform inference on images. You can upload your images and get predictions using this API. Here’s a basic example of how you can use the API to detect objects in images:
Web Application Integration: If you want to integrate this into a web application, you can use frameworks like Flask or Django (for Python) to create an endpoint that handles image uploads, calls the Ultralytics HUB API, and returns the predictions.
Ultralytics HUB App: You can also use the Ultralytics HUB App to preview and test your model directly on the platform. This is a great way to quickly validate your model's performance on new images.
For more detailed information, you can refer to the Ultralytics HUB Quickstart Guide.
If you encounter any issues or have further questions, feel free to ask. We're here to help! 😊
github-actions commentedon Nov 23, 2025
👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.
For additional resources and information, please see the links below:
Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!
Thank you for your contributions to YOLO 🚀 and Vision AI ⭐
glenn-jocher commentedon Jul 7, 2026
Hi @sylenola, revisiting this since HUB winds down on July 31, 2026: what you asked for — running your trained model on images online — is now built into Ultralytics Platform. Every model page has a Predict tab for browser inference with no local setup, and for batches of images you can create a dedicated endpoint and POST images to it from any language.
glenn-jocher commentedon Nov 18, 2026
Hi @sylenola, running your trained model on images online is answered above and is now built into the Predict tab of every model on Ultralytics Platform. I'm closing this as resolved. Please reopen if you run into problems.