|
|
--- |
|
|
library_name: transformers |
|
|
license: other |
|
|
base_model: nvidia/mit-b0 |
|
|
tags: |
|
|
- vision |
|
|
- image-segmentation |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: segformer-b0-finetuned-segments-satellite-terrain |
|
|
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-segments-satellite-terrain |
|
|
|
|
|
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the ZeeeWP/terrain_map dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.8455 |
|
|
- Mean Iou: 0.1918 |
|
|
- Mean Accuracy: 0.3314 |
|
|
- Overall Accuracy: 0.4947 |
|
|
- Accuracy Unlabeled: nan |
|
|
- Accuracy Sand: 0.4672 |
|
|
- Accuracy Cliff: 0.6054 |
|
|
- Accuracy Bedrock flat: 0.6452 |
|
|
- Accuracy Bedrock lowhill: 0.2043 |
|
|
- Accuracy Bedrock highhill: 0.1049 |
|
|
- Accuracy Gravel low hill: 0.2929 |
|
|
- Accuracy Gravel high hill: 0.0 |
|
|
- Iou Unlabeled: 0.0 |
|
|
- Iou Sand: 0.2825 |
|
|
- Iou Cliff: 0.4353 |
|
|
- Iou Bedrock flat: 0.4798 |
|
|
- Iou Bedrock lowhill: 0.0568 |
|
|
- Iou Bedrock highhill: 0.0362 |
|
|
- Iou Gravel low hill: 0.2437 |
|
|
- Iou Gravel high hill: 0.0 |
|
|
|
|
|
## 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: 4 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Sand | Accuracy Cliff | Accuracy Bedrock flat | Accuracy Bedrock lowhill | Accuracy Bedrock highhill | Accuracy Gravel low hill | Accuracy Gravel high hill | Iou Unlabeled | Iou Sand | Iou Cliff | Iou Bedrock flat | Iou Bedrock lowhill | Iou Bedrock highhill | Iou Gravel low hill | Iou Gravel high hill | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:--------------:|:---------------------:|:------------------------:|:-------------------------:|:------------------------:|:-------------------------:|:-------------:|:--------:|:---------:|:----------------:|:-------------------:|:--------------------:|:-------------------:|:--------------------:| |
|
|
| 1.7741 | 5.0 | 20 | 1.9971 | 0.1727 | 0.3113 | 0.4575 | nan | 0.4371 | 0.6817 | 0.5485 | 0.1547 | 0.2136 | 0.1422 | 0.0012 | 0.0 | 0.2559 | 0.4600 | 0.4535 | 0.0433 | 0.0367 | 0.1315 | 0.0010 | |
|
|
| 1.6412 | 10.0 | 40 | 1.8455 | 0.1918 | 0.3314 | 0.4947 | nan | 0.4672 | 0.6054 | 0.6452 | 0.2043 | 0.1049 | 0.2929 | 0.0 | 0.0 | 0.2825 | 0.4353 | 0.4798 | 0.0568 | 0.0362 | 0.2437 | 0.0 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.3 |
|
|
- Pytorch 2.4.1+cu121 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
|
|
|
