|
--- |
|
license: other |
|
base_model: nvidia/mit-b0 |
|
tags: |
|
- vision |
|
- image-segmentation |
|
- generated_from_trainer |
|
model-index: |
|
- name: segformer-b0-finetuned-v0 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# segformer-b0-finetuned-v0 |
|
|
|
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the tontokoton/artery-ultrasound-siit dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5847 |
|
- Mean Iou: 0.1252 |
|
- Mean Accuracy: 0.2052 |
|
- Overall Accuracy: 0.2652 |
|
- Accuracy Artery: nan |
|
- Accuracy Vein: 0.2256 |
|
- Accuracy Nerve: 0.0 |
|
- Accuracy Muscle1: 0.0 |
|
- Accuracy Muscle2: 0.3266 |
|
- Accuracy Muscle3: 0.0009 |
|
- Accuracy Muscle4: 0.6780 |
|
- Accuracy Unknown: nan |
|
- Iou Artery: 0.0 |
|
- Iou Vein: 0.2256 |
|
- Iou Nerve: 0.0 |
|
- Iou Muscle1: 0.0 |
|
- Iou Muscle2: 0.2135 |
|
- Iou Muscle3: 0.0005 |
|
- Iou Muscle4: 0.4366 |
|
- Iou Unknown: nan |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 6e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Artery | Accuracy Vein | Accuracy Nerve | Accuracy Muscle1 | Accuracy Muscle2 | Accuracy Muscle3 | Accuracy Muscle4 | Accuracy Unknown | Iou Artery | Iou Vein | Iou Nerve | Iou Muscle1 | Iou Muscle2 | Iou Muscle3 | Iou Muscle4 | Iou Unknown | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:---------------:|:-------------:|:--------------:|:----------------:|:----------------:|:----------------:|:----------------:|:----------------:|:----------:|:--------:|:---------:|:-----------:|:-----------:|:-----------:|:-----------:|:-----------:| |
|
| 1.7835 | 10.0 | 10 | 1.9744 | 0.0620 | 0.1572 | 0.2117 | nan | 0.0834 | 0.0 | 0.0 | 0.2330 | 0.0002 | 0.6266 | nan | 0.0 | 0.0563 | 0.0 | 0.0 | 0.1422 | 0.0001 | 0.2975 | 0.0 | |
|
| 1.4779 | 20.0 | 20 | 1.8578 | 0.0954 | 0.1794 | 0.2576 | nan | 0.0670 | 0.0 | 0.0 | 0.3099 | 0.0 | 0.6992 | nan | 0.0 | 0.0670 | 0.0 | 0.0 | 0.1857 | 0.0 | 0.4152 | nan | |
|
| 1.3434 | 30.0 | 30 | 1.6759 | 0.1239 | 0.2014 | 0.2743 | nan | 0.1921 | 0.0 | 0.0 | 0.3566 | 0.0 | 0.6594 | nan | 0.0 | 0.1921 | 0.0 | 0.0 | 0.2244 | 0.0 | 0.4509 | nan | |
|
| 1.2779 | 40.0 | 40 | 1.6276 | 0.1375 | 0.2263 | 0.3176 | nan | 0.2159 | 0.0 | 0.0 | 0.4348 | 0.0 | 0.7073 | nan | 0.0 | 0.2159 | 0.0 | 0.0 | 0.2784 | 0.0 | 0.4684 | nan | |
|
| 1.1988 | 50.0 | 50 | 1.5847 | 0.1252 | 0.2052 | 0.2652 | nan | 0.2256 | 0.0 | 0.0 | 0.3266 | 0.0009 | 0.6780 | nan | 0.0 | 0.2256 | 0.0 | 0.0 | 0.2135 | 0.0005 | 0.4366 | nan | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|