okinawa-ai-beach-robot/yolov5s_beachbot_160

Model Card for yolo5_beachbot_160

Model Details

Model Description

A finetune of Yolo5 intended for identifying beach trash.

• Developed by: Jeffrey Queisser, Christopher Buckley
• Funded by: Okinawa Institute of Science and Technology COI Next Grant
• Model type: Yolo5
• License: CC BY-NC 4.0
• Finetuned from model: Yolo5

Model Sources

• Repository: https://github.com/okinawa-ai-beach-robot/yolo5_beachbot_160
• Demo: [Work in Progress]

Bias, Risks, and Limitations

    Note the dataset is small and test set can have quite similar images to the train set. 
    This was an early version of the dataset so results are not reliable
    

Recommendations

    Use later version of the dataset
    

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

https://universe.roboflow.com/okinawaaibeachrobot/beach-cleaning-object-detection/dataset/1

Training Procedure

Preprocessing

    {'preprocessing': {'auto-orient': True, 'resize': {'width': 1280, 'height': 800, 'format': 'Fill (with center crop) in'}}}
    See https://docs.roboflow.com/api-reference/versions/create-a-project-version for more information
    

Training Hyperparameters

• Training regime: TODO populate with any hyperparameters

Evaluation

Testing Data, Factors & Metrics

Testing Data

https://universe.roboflow.com/okinawaaibeachrobot/beach-cleaning-object-detection/dataset/1/images?split=test

Metrics

    TODO populate with any metrics
    e.g. loss function
    

Results

    TODO populate with any results
    

Technical Specifications

Model Card Authors

Christopher Buckley

Model Card Contact

https://github.com/okinawa-ai-beach-robot/home/discussions