|
--- |
|
library_name: transformers |
|
license: other |
|
base_model: nvidia/mit-b0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- scene_parse_150 |
|
model-index: |
|
- name: segformer-b0-scene-parse-150 |
|
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-scene-parse-150 |
|
|
|
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the scene_parse_150 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.5313 |
|
- Mean Iou: 0.0247 |
|
- Mean Accuracy: 0.0606 |
|
- Overall Accuracy: 0.2947 |
|
- Per Category Iou: [0.06616146494205827, 0.3681700970509635, 0.0014878707677961685, 0.9162769876481256, 0.0, 0.5636441979126612, 0.0, 0.0, 0.0, 0.0, 0.002809019586327975, 0.0, nan, 0.0, 0.0, 0.0, 4.201327619527771e-05, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.005037440435670524, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan] |
|
- Per Category Accuracy: [0.29468704487548986, 0.49082289260924866, 0.156227501799856, 0.9651341594536313, 0.0, 0.9311171279131057, 0.0, nan, 0.0, 0.0, 0.002842817720970778, 0.0, nan, 0.0, nan, nan, 4.592949822023194e-05, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.008962454582155834, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 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: 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| |
|
| 4.636 | 4.0 | 20 | 4.8633 | 0.0143 | 0.0490 | 0.2505 | [0.06117991800032897, 0.2538067166642009, 0.0, 0.8617166061786316, 0.0, 0.5500544538802781, 0.0, 0.0, 0.0, 0.0, 0.002095025967295542, 0.0, 0.0, 0.0, 0.0, 0.0, 0.017959296883125888, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 4.291477126426916e-05, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan] | [0.27402119451957613, 0.278794678434032, 0.0, 0.9355842408443006, 0.0, 0.7758986534277, 0.0, nan, 0.0, 0.0, 0.002109903777282999, 0.0, nan, 0.0, nan, nan, 0.03568722011712022, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, 8.074283407347598e-05, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan] | |
|
| 4.3052 | 8.0 | 40 | 4.5313 | 0.0247 | 0.0606 | 0.2947 | [0.06616146494205827, 0.3681700970509635, 0.0014878707677961685, 0.9162769876481256, 0.0, 0.5636441979126612, 0.0, 0.0, 0.0, 0.0, 0.002809019586327975, 0.0, nan, 0.0, 0.0, 0.0, 4.201327619527771e-05, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.005037440435670524, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan] | [0.29468704487548986, 0.49082289260924866, 0.156227501799856, 0.9651341594536313, 0.0, 0.9311171279131057, 0.0, nan, 0.0, 0.0, 0.002842817720970778, 0.0, nan, 0.0, nan, nan, 4.592949822023194e-05, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.008962454582155834, nan, nan, nan, 0.0, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan] | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
