yolos-small-Abdomen_MRI
This model is a fine-tuned version of hustvl/yolos-small.
Model description
https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Computer%20Vision/Object%20Detection/Abdomen%20MRIs%20Object%20Detection/Abdomen_MRI_Object_Detection_YOLOS.ipynb
Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
Training and evaluation data
Dataset Source: https://huggingface.co/datasets/Francesco/abdomen-mri
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Metric Name | IoU | Area | maxDets | Value |
|---|---|---|---|---|
| Average Precision (AP) | 0.50:0.95 | all | 100 | 0.453 |
| Average Precision (AP) | 0.50 | all | 100 | 0.928 |
| Average Precision (AP) | 0.75 | all | 100 | 0.319 |
| Average Precision (AP) | 0.50:0.95 | small | 100 | -1.000 |
| Average Precision (AP) | 0.50:0.95 | medium | 100 | 0.426 |
| Average Precision (AP) | 0.50:0.95 | large | 100 | 0.457 |
| Average Recall (AR) | 0.50:0.95 | all | 1 | 0.518 |
| Average Recall (AR) | 0.50:0.95 | all | 10 | 0.645 |
| Average Recall (AR) | 0.50:0.95 | all | 100 | 0.715 |
| Average Recall (AR) | 0.50:0.95 | small | 100 | -1.000 |
| Average Recall (AR) | 0.50:0.95 | medium | 100 | 0.633 |
| Average Recall (AR) | 0.50:0.95 | large | 100 | 0.716 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3
