Comments (1)
Hello! π It looks like you're encountering an issue where the input size during the export doesn't match the model's maximum input size specified during the conversion process.
When exporting your model to TensorRT using a custom imgsz
(image size), ensure that the exported model's inference input size matches the specified imgsz
. The error you're encountering typically happens when there's a mismatch in the sizes expected by the model.
You can try specifying the imgsz
during inference to match the size used during the export. Here's a snippet that might help:
# Assuming you've already exported your model as shown in your question...
# Load your TensorRT model
model_trt = YOLO('path_to_exported_engine_file.engine')
# Specify the same imgsz for inference
results = model_trt.predict('path_to_your_image_or_video', imgsz=2048)
This makes sure that both during export and inference, the model works with the same image dimensions, thus avoiding any size mismatch issues.
If you continue experiencing issues or have more questions, feel free to ask. Good luck! π
from ultralytics.
Related Issues (20)
- Training strategy on the Open Image V7 dataset HOT 1
- How to disable request to www.google-analytics.com? HOT 10
- PGI Implementation HOT 3
- Getting yolov8-pose onnx model output 1 x 56 x 8400 ? What's the possible fix in Javascript? HOT 1
- Yolo v8 what does deterministic parameter do? HOT 2
- UnsupportedModelRegistryStoreURIException: Model registry functionality is unavailable; got unsupported URI HOT 6
- How to use focal loss function in yolov8? HOT 5
- Cold start Slow inference HOT 2
- Problems in yolov8 training HOT 1
- RTSP path is changed from the defined url when inference
- Error Implementing model training using YOLOv8 on Android HOT 2
- <A bug in Data Augmentation>YOLOv8-OBB HOT 9
- Error reported when setting model single channel ch: 1 HOT 8
- No labels found HOT 6
- AttributeError: 'Segment' object has no attribute 'detect' HOT 10
- Custom copy_paste augmentation HOT 2
- Why are the max_channels in the backbone of the classification model and the detection model different? HOT 5
- γBUG?γAngle error issue HOT 3
- TaskAlignedAssigner doesn't take into account `reg_max` which affects prediction of large objects HOT 2
- How to read onnx and obtain names, imgsz HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ultralytics.