Welcome to the repository JunkWaxDetection, hosted by the GitHub organization JunkWaxData. This Machine Learning model is designed to identify sports cards from the overproduced "junk wax" era (1985–1996), with exceptional precision and recall metrics. Whether you're a collector, seller, or enthusiast, this model can streamline the identification of cards from various iconic sets.
- Model Version: Iteration 26
- Domain: General (compact) [S1]
- Precision: 98.7%
- Recall: 98.4%
- mAP: 99.8%
| Tag | Precision | Recall | Average Precision (AP) |
|---|---|---|---|
| 1982 Donruss | 100.0% | 100.0% | 100.0% |
| 1984 Topps | 100.0% | 100.0% | 100.0% |
| 1987 Fleer | 95.5% | 95.5% | 99.8% |
| 1987 Topps | 100.0% | 100.0% | 100.0% |
| 1988 Donruss | 95.5% | 100.0% | 100.0% |
| 1988 Donruss Pack | 100.0% | 100.0% | 100.0% |
| 1988 Fleer | 100.0% | 85.7% | 100.0% |
| 1988 Fleer Pack | 100.0% | 100.0% | 100.0% |
| 1988 Score | 100.0% | 100.0% | 100.0% |
| 1988 Topps | 96.0% | 100.0% | 99.7% |
| 1988 Topps Pack | 100.0% | 100.0% | 100.0% |
| 1989 Bowman | 100.0% | 100.0% | 100.0% |
| 1989 Donruss | 100.0% | 100.0% | 100.0% |
| 1989 Donruss Pack | 100.0% | 100.0% | 100.0% |
| 1989 Fleer | 100.0% | 100.0% | 100.0% |
| 1989 Score | 100.0% | 100.0% | 100.0% |
| 1989 Topps | 95.2% | 95.2% | 99.6% |
| 1989 Topps Pack | 100.0% | 91.7% | 100.0% |
| 1989 Upper Deck | 100.0% | 100.0% | 100.0% |
| 1990 Donruss | 96.2% | 100.0% | 100.0% |
| 1990 Donruss Pack | 100.0% | 100.0% | 100.0% |
| 1990 Fleer | 100.0% | 96.9% | 99.7% |
| 1990 Fleer Pack | 100.0% | 100.0% | 100.0% |
| 1990 Leaf | 100.0% | 100.0% | 100.0% |
| 1990 Leaf Pack | 100.0% | 100.0% | 100.0% |
| 1990 Topps | 100.0% | 100.0% | 100.0% |
| 1990 Upper Deck High Series Pack | 100.0% | 100.0% | 100.0% |
| 1991 Donruss Series 1 Pack | 71.4% | 100.0% | 100.0% |
| 1991 Donruss Series 2 Pack | 100.0% | 100.0% | 100.0% |
| 1991 Fleer | 100.0% | 100.0% | 100.0% |
| 1991 Fleer Ultra | 100.0% | 100.0% | 100.0% |
| 1991 Leaf | 100.0% | 95.5% | 95.5% |
| 1991 Leaf Pack | 100.0% | 25.0% | 100.0% |
| 1991 Score | 100.0% | 100.0% | 100.0% |
| 1991 Topps | 100.0% | 100.0% | 100.0% |
| 1991 Topps Pack | 100.0% | 100.0% | 100.0% |
| 1991 Upper Deck | 100.0% | 89.5% | 99.5% |
| 1991 Upper Deck Low Series Pack | 100.0% | 100.0% | 100.0% |
| 1992 Donruss Series 2 Pack | 100.0% | 100.0% | 100.0% |
| 1992 Fleer | 95.5% | 100.0% | 100.0% |
| 1992 Fleer Pack | 100.0% | 75.0% | 100.0% |
| 1992 Fleer Ultra | 100.0% | 100.0% | 100.0% |
| 1992 Leaf | 100.0% | 100.0% | 100.0% |
| 1992 O-Pee-Chee Premiere | 100.0% | 100.0% | 100.0% |
| 1992 Pinnacle | 94.7% | 100.0% | 99.7% |
| 1992 Pinnacle Pack | 100.0% | 100.0% | 100.0% |
| 1992 Upper Deck | 95.8% | 95.8% | 95.7% |
| 1992 Upper Deck High Series Pack | 100.0% | 100.0% | 100.0% |
| 1993 Fleer | 95.2% | 100.0% | 100.0% |
| 1993 Fleer Series 1 Pack | 100.0% | 100.0% | 100.0% |
| 1993 Fleer Series 2 Pack | 100.0% | 100.0% | 100.0% |
| 1993 Topps | 91.3% | 95.5% | 99.6% |
| 1994 Leaf | 100.0% | 100.0% | 100.0% |
| 1994 Pinnacle | 100.0% | 100.0% | 100.0% |
| 1994 Score | 100.0% | 100.0% | 100.0% |
| 1995 Leaf | 100.0% | 100.0% | 100.0% |
| 1995 Select | 100.0% | 100.0% | 100.0% |
| 1996 Pinnacle | 100.0% | 100.0% | 100.0% |
-
model- Contains the ONNX and TensorFlow model files. -
src- Example projects demonstrating how to use the models.
- Clone this repository to your local machine.
git clone https://github.com/JunkWaxData/JunkWaxDetection.git
- Navigate to the
srcfolder for example code in various programming languages. - Load the model in your preferred framework and integrate it into your project.
- Python (ONNXRuntime)
- C# (ML.NET)
- JavaScript (TensorFlow.js)
Feel free to explore the src folder for detailed implementation examples. Contributions in other languages are encouraged!
We encourage community contributions! Whether it's submitting your own example project or improving documentation, we welcome your input.
This project is licensed under the MIT License. By contributing, you agree to license your work under the same terms.
For any inquiries, please reach out to us at [email protected].