Comments (2)
Hello! It looks like you've encountered issues regarding input parameters and output resizing when converting from a PyTorch .pt
model to an .onnx
format. Here are some insights to help address these:
-
Input Parameters (task and imgsz): When exporting to ONNX and using it, you might need to explicitly specify these parameters that are automatically handled in the PyTorch version. This difference often comes due to the static nature of ONNX which needs definite input sizes and tasks specified.
-
Output Resizing and Padding: ONNX models sometimes behave differently due to the static graph constraints. ONNX requires fixed dimensions (
imgsz
) for all operations within the model, which might lead to additional resizing and zero-padding not present in the dynamical PyTorch version.
To remedy resizing and padding issues, you can adjust the post-processing of the output in your application to align with how the .pt
model handles these aspects. Here is sample code to adjust the output:
# Assuming `results` is the output of the ONNX model
import numpy as np
def resize_masks(masks, original_shape):
out = [cv2.resize(mask, (original_shape[1], original_shape[0]), interpolation=cv2.INTER_LINEAR) for mask in masks]
return np.array(out)
original_shape = cropped_image.shape[:2] # Assuming cropped_image shape is HxWxC
resized_masks = resize_masks(results.masks, original_shape)
Please refer to the Ultralytics documentation on model export for details on how configurations may affect ONNX outputs compared to PyTorch. If the issue persists, consider using our support channels where we can examine your case more closely. Let us know if this was helpful! 🚀
from ultralytics.
👋 Hello @liuy129, 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.
Related Issues (20)
- Wandb gives wrong label for x-axis HOT 1
- Box Loss with Polygon Labels HOT 1
- Hardware resources required for model deployment HOT 2
- How to get image_buffer inference name of result HOT 1
- How to crop an image and save the full box HOT 1
- Overlapping Masks in YOLOv8 Segmentation. "agnostic_nms" doesn't work the way I want. HOT 6
- Request for Official C++ and TensorRT Support HOT 2
- Issue accessing box_loss, cls_loss, and dfl_loss in on_train_epoch_end callback HOT 2
- What are differences between single image vs multiple images predict? HOT 1
- how model yaml gets initiated ? HOT 1
- the ultralytics file in my yolov8 suddenly disappear HOT 2
- Yolov8 tensorflow js HOT 6
- Multiple streams breaks once the model is converted to ONNX HOT 4
- Doesn't batch size increase benefit engine export anymore? HOT 8
- 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 2
- 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 3
- How to display OKS scores 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.