|
--- |
|
license: other |
|
base_model: nvidia/segformer-b0-finetuned-ade-512-512 |
|
tags: |
|
- vision |
|
- image-segmentation |
|
- generated_from_trainer |
|
model-index: |
|
- name: segformer_finetuned_coasts |
|
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_finetuned_coasts |
|
|
|
This model is a fine-tuned version of [nvidia/segformer-b0-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b0-finetuned-ade-512-512) on the peldrak/coast dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9618 |
|
- Mean Iou: 0.2104 |
|
- Mean Accuracy: 0.2661 |
|
- Overall Accuracy: 0.7259 |
|
- Accuracy Water: nan |
|
- Accuracy Whitewater: 0.0519 |
|
- Accuracy Sediment: 0.0150 |
|
- Accuracy Other Natural Terrain: 0.0024 |
|
- Accuracy Vegetation: 0.5470 |
|
- Accuracy Development: 0.0259 |
|
- Accuracy Unknown: 0.9547 |
|
- Iou Water: 0.0 |
|
- Iou Whitewater: 0.0160 |
|
- Iou Sediment: 0.0134 |
|
- Iou Other Natural Terrain: 0.0022 |
|
- Iou Vegetation: 0.4628 |
|
- Iou Development: 0.0254 |
|
- Iou Unknown: 0.9532 |
|
|
|
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 0.05 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Water | Accuracy Whitewater | Accuracy Sediment | Accuracy Other Natural Terrain | Accuracy Vegetation | Accuracy Development | Accuracy Unknown | Iou Water | Iou Whitewater | Iou Sediment | Iou Other Natural Terrain | Iou Vegetation | Iou Development | Iou Unknown | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:--------------:|:-------------------:|:-----------------:|:------------------------------:|:-------------------:|:--------------------:|:----------------:|:---------:|:--------------:|:------------:|:-------------------------:|:--------------:|:---------------:|:-----------:| |
|
| 1.7548 | 0.01 | 20 | 1.3306 | 0.1980 | 0.3291 | 0.6833 | nan | 0.5156 | 0.0933 | 0.0701 | 0.2872 | 0.0553 | 0.9531 | 0.0 | 0.0267 | 0.0755 | 0.0363 | 0.2664 | 0.0349 | 0.9461 | |
|
| 1.5812 | 0.02 | 40 | 1.0977 | 0.2226 | 0.2976 | 0.7293 | nan | 0.1333 | 0.0446 | 0.0449 | 0.5497 | 0.0618 | 0.9509 | 0.0 | 0.0191 | 0.0357 | 0.0298 | 0.4724 | 0.0520 | 0.9489 | |
|
| 1.3861 | 0.04 | 60 | 1.0240 | 0.2251 | 0.2920 | 0.7480 | nan | 0.0760 | 0.0161 | 0.0261 | 0.6433 | 0.0341 | 0.9564 | 0.0 | 0.0162 | 0.0144 | 0.0189 | 0.5387 | 0.0327 | 0.9549 | |
|
| 1.023 | 0.05 | 80 | 0.9618 | 0.2104 | 0.2661 | 0.7259 | nan | 0.0519 | 0.0150 | 0.0024 | 0.5470 | 0.0259 | 0.9547 | 0.0 | 0.0160 | 0.0134 | 0.0022 | 0.4628 | 0.0254 | 0.9532 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|
