Comments (5)
👋 Hello @centurions, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.
If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.
If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.
Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.
Install
Pip install the ultralytics
package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.
pip install ultralytics
Environments
YOLOv8 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):
- Notebooks with free GPU:
- Google Cloud Deep Learning VM. See GCP Quickstart Guide
- Amazon Deep Learning AMI. See AWS Quickstart Guide
- Docker Image. See Docker Quickstart Guide
Status
If this badge is green, all Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.
from ultralytics.
@centurions hello! It looks like the issue you're encountering during prediction with the ONNX model might be related to the output tensor dimensions expected by the post-processing function. The error suggests that the output tensor shape does not match the expected shape, which is causing the assertion error.
A potential solution is to verify the output shapes of your ONNX model to ensure they match what the YOLOv8 framework expects for classification tasks. You can use tools like Netron to visualize the ONNX model and check the output dimensions.
If the dimensions are indeed different, you might need to adjust the export settings or modify the post-processing code to handle the shape returned by your ONNX model. Here's a quick way to check the output shape using ONNX:
import onnx
import onnxruntime as ort
# Load your model
onnx_model = onnx.load("best.onnx")
onnx.checker.check_model(onnx_model)
# Create a session and get the output
ort_session = ort.InferenceSession("best.onnx")
outputs = ort_session.run(None, {'input': your_input_tensor})
print('Output shape:', outputs[0].shape)
Adjust your_input_tensor
to match the input size your model expects. This snippet will help you confirm if the output dimensions are as expected.
If you continue to experience issues, please provide more details about the output shapes, and we can explore further adjustments!
from ultralytics.
Hello Thank you
I have same error with openvino and others. I couldn't solve it. Do you have any other idea how it can be solved?
from ultralytics.
Hello @centurions,
Thank you for your patience. The issue seems to be consistent across multiple export formats, indicating it might be related to the output tensor dimensions expected by the post-processing function.
To troubleshoot further, I recommend checking the output shapes of your exported models. You can use tools like Netron to visualize the model and ensure the output dimensions match what YOLOv8 expects for classification tasks.
Additionally, you can inspect the output shapes using the following code snippet for ONNX:
import onnx
import onnxruntime as ort
# Load your model
onnx_model = onnx.load("best.onnx")
onnx.checker.check_model(onnx_model)
# Create a session and get the output
ort_session = ort.InferenceSession("best.onnx")
outputs = ort_session.run(None, {'input': your_input_tensor})
print('Output shape:', outputs[0].shape)
Replace your_input_tensor
with the appropriate input tensor for your model. This will help confirm if the output dimensions are as expected.
If the issue persists, please share the output shapes, and we can explore further adjustments. Feel free to reach out if you need more assistance! 😊
from ultralytics.
@centurions perhaps you could try downgrading your torch
install? I've seen other users having some issues with torch==2.3.0
and I was able to successful export and run inference using some of the standard assets.
from ultralytics.
Related Issues (20)
- Bug heatmap ultralytics 8.1.34 HOT 3
- How do I get the coordinates of detected objects in yolov8 in real time and print? HOT 5
- Seeking Guidance on Integrating SuperPoint with YOLOv8 for Improved Keypoint and Object Detection HOT 2
- show_labels=False, show_conf=False parameters won't work (ultralytics==8.2.25) HOT 4
- Custom callback function HOT 7
- How to display OKS scores HOT 3
- Using OBB for pick and place on a robotic arm HOT 2
- Object Counting HOT 2
- Results of the same images different when used in validation or prediction HOT 2
- custom model architecture plot HOT 1
- Custom model in YOLOv8 HOT 3
- Custom Model Can Not Detection Object When Converted CoreML HOT 8
- Discrepancy in confusion matrix and Prediction.jon HOT 1
- Preprocessing bottleneck in YOLOv8 Classification HOT 17
- MacOS error with TFLite model inference end2end model
- Segmentation for RTDERT HOT 2
- Change evaluation period HOT 4
- How does the confusion matrix of the object detection module works? HOT 3
- Difference between C2f and C2 HOT 4
- anchors of yolov8 HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ultralytics.