Comments (6)
@Burhan-Q, Thanks for the advice, I'll try
from hub.
π Hello @Barmark-learn, thank you for raising an issue about Ultralytics HUB π! Please visit our HUB Docs to learn more:
- Quickstart. Start training and deploying YOLO models with HUB in seconds.
- Datasets: Preparing and Uploading. Learn how to prepare and upload your datasets to HUB in YOLO format.
- Projects: Creating and Managing. Group your models into projects for improved organization.
- 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.
- Inference API. Understand how to use the Inference API for running your trained models in the cloud to generate predictions.
If this is a π Bug Report, please provide screenshots and steps to reproduce your problem to help us get started working on a fix.
If this is a β 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!
from hub.
@Barmark-learn hello! I'm sorry to hear you're experiencing issues with adding your own dataset to the Ultralytics HUB. Let's try to troubleshoot this together. π οΈ
First, please ensure that your dataset directory structure strictly follows the required format as outlined in our documentation. The error message you're seeing typically indicates that there might be a mismatch in the expected file paths.
Here are a few things to double-check:
- Confirm that your image files are indeed within the specified 'images' folder.
- Verify that the annotations are correctly placed in the corresponding 'labels' folder and that they match the format specified in the documentation.
- Make sure that there are no typos or discrepancies in the folder names or the paths within your dataset configuration.
If you've confirmed all the above and the issue persists, it might be helpful to review the dataset's configuration file for any errors or omissions.
For further detailed guidance on dataset structure and troubleshooting, please refer to the Ultralytics HUB Docs. If the problem continues after reviewing the documentation, please provide us with the exact error message and a description of your dataset structure so we can assist you more effectively.
We appreciate your patience and are here to help you get your dataset up and running! π
from hub.
@Barmark-learn I was troubleshooting this with someone recently. This is how I structured my directory and was able to get the data to upload (I only made a small dataset of 20 images for testing)
data
ββββdata-seg20
ββββdata.yaml
ββββtrain
β ββββimages
β ββββlabels
ββββvalid
ββββimages
ββββlabels
You can also verify your dataset locally for HUB using
from ultralytics.hub import check_dataset
check_dataset('Q:\data\data-seg20.zip', task="segment")
which will show (I was using segment
data):
Starting HUB dataset checks for Q:\data\data-seg20.zip....
WARNING β οΈ Skipping Q:\data\data-seg20.zip unzip as destination directory Q:\data\data-seg20 is not empty.
Scanning Q:\data\data-seg20\train\labels... 20 images, 0 backgrounds, 0 corrupt: 100%|ββββββββββ| 20/20 [00:00<00:00, 1254.80it/s]
New cache created: Q:\data\data-seg20\train\labels.cache
Statistics: 100%|ββββββββββ| 20/20 [00:00<?, ?it/s]
Scanning Q:\data\data-seg20\valid\labels... 20 images, 0 backgrounds, 0 corrupt: 100%|ββββββββββ| 20/20 [00:00<00:00, 1666.92it/s]
New cache created: Q:\data\data-seg20\valid\labels.cache
Statistics: 100%|ββββββββββ| 20/20 [00:00<?, ?it/s]
Checks completed correctly β
. Upload this dataset to https://hub.ultralytics.com/datasets/.
from hub.
Pycharm tells me is correct, but i can't upload my datasets
Unzipping /Users/zhuxinchen/PycharmProjects/pythonProject3/i think i can.v1i.yolov5pytorchηε―ζ¬.zip to /Users/zhuxinchen/PycharmProjects/pythonProject3/i think i can.v1i.yolov5pytorch...: 100%|ββββββββββ| 7/7 [00:00<00:00, 1199.89file/s]
Checks completed correctly β
. Upload this dataset to https://hub.ultralytics.com/datasets/.
from hub.
@jackbrown333 see examples in my comment here about what will work for dataset structuring for HUB
from hub.
Related Issues (20)
- Why canβt I continue training in cloud? HOT 4
- PROBLEM ABOUT THE DEPLOYMENT OF THE MODEL TO THE HARDWARE. HOT 4
- Resume training not available for cloud trained model/ HOT 5
- Multi-GPU does not upload to Hub Web HOT 5
- Model not trained but balance subtracted HOT 10
- error on preview HOT 3
- Trained model Preview Error : An error has occurred, pls try again later HOT 4
- On demand balance being drained far faster than actual usage HOT 4
- TensorFlow Lite model deployment results HOT 2
- Tensorflow lite model with fp16& int8 optimisations detections accuracy in android comparison with preview feature of HUB HOT 2
- Getting unexpred shape from model output HOT 5
- Ultralytics HUB: Received no response from the request HOT 4
- Ultralytics Hub have RTDETR? HOT 4
- Subscription Billing Receipt HOT 12
- Incorrect README redirect for 2nd Ultralytics HUB link HOT 4
- connection issue HOT 3
- Choosing Yolov8 OBB model when selecting model to train with HOT 4
- Epochs remaining gone negative and stuck on optimising weights HOT 12
- How to display the key point coordinates of yolov8 detection target HOT 2
- Can't test training with coco2017 dataset HOT 2
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 hub.