## Dataset Information
The dataset focuses on the printed part of 316ss track prints that were one a 316ss substrate. This was done in-situ and using Lawrence Livermore National Laboratory on board High Speed Camera video recorder for laser powder bed fusion.
Currently, the dataset consists of 100 annotated images.
#### **Instructions for Generating Predictions and Evaluating Model Performance on the Benchmark Dataset**
- Raw images and corresponding groud truth masks are [here][1].
- For each model, we provide an inference script to generate predictions.
- Refer to the table at the bottom for links to the inference scripts for each model.
- You need to change the paths for images and model in the script accordingly.
- Once you've generated the predictions, you can use the '[get_evaluation_metrics.py][2]' script (applicable to all models in this dataset) to assess the model's performance on the generated predictions.
- You need to change the paths for images in the script accordingly.
**Metadata:**
- Maker = Mikrotron
- Model = MC1362
- Detector = CMOS Sensor
- dimension size = 1280x1024
- Capture Rate = 1kHz
- wavelength detection = 1024 gray levels
- resolution limit = 14 μm/pixel
- Orientation = Co-axial
- filter band pass = 780−820 nm
- video output dimensions = 256 × 256
- measure scale = 17 μm/pixel
- exposure time = 200 μs
**Want to contribute? Fill up this [Google Form][3]**.
<h2>
Benchmarks
</h2>
| Model | Description | Binary IoU | Library | Input Image Size | Performance Metrics | Paper | Evaluation Script |Compatible TensorFlow Version |
|:---------------------------------:|:--------------------------------------------:|:----------:|:--------------------:|:----------------:|:------------------------------------------:|:------------------------------------------:|:------------------------------------------:|:------------------------------------------:|
| [unet.h5][4] | U-Net model with 4-block encoder and decoder | 23%|Tensorflow/Keras | 1024 x 1024| Accuracy <br> Precision <br> Recall <br> Binary IoU* | - | [Click Here][5] |TensorFlow 2.13.0 |
[1]: https://osf.io/dzv3b/files/osfstorage
[2]: https://osf.io/download/6707ebac3c04be001f210fc5/
[3]: https://osf.io/download/6707ebac3c04be001f210fc5/
[4]: https://osf.io/download/6658e77e65e1de4893894165/
[5]: https://osf.io/download/6707ebac9bf7741c44a5eef1/
